Documents

43 entities and 235 agent-callable operations in documents. Each operation is addressed as {mega_tool}/documents/{entity}/{operation} and carries the same permission check over MCP and REST.

`access_grant`

Operation	Mega-tool	What it does
`list`	`entity_crud`	List access_grants with filtering and pagination
`read`	`entity_crud`	Get detailed access grant information
`search`	`entity_crud`	Search access_grants with fuzzy matching

`access_scope`

Operation	Mega-tool	What it does
`list`	`entity_crud`	List access_scopes with filtering and pagination
`read`	`entity_crud`	Get detailed access scope information
`search`	`entity_crud`	Search access_scopes with fuzzy matching

`attachment`

Operation	Mega-tool	What it does
`codex_judge_sweep`	`workflow_action`	Size or sample the headless-Codex content judge for never-content-judged email attachments.

`dedup_rule`

Operation	Mega-tool	What it does
`create`	`entity_crud`	Create a new dedup rule
`delete`	`entity_crud`	Delete a dedup rule
`list`	`entity_crud`	List dedup_rules with filtering and pagination
`read`	`entity_crud`	Get detailed dedup rule information
`search`	`entity_crud`	Search dedup_rules with fuzzy matching
`update`	`entity_crud`	Update an existing dedup rule

`dedup_rule_set`

Operation	Mega-tool	What it does
`create`	`entity_crud`	Create a new dedup rule set
`delete`	`entity_crud`	Delete a dedup rule set
`list`	`entity_crud`	List dedup_rule_sets with filtering and pagination
`read`	`entity_crud`	Get detailed dedup rule set information
`search`	`entity_crud`	Search dedup_rule_sets with fuzzy matching
`update`	`entity_crud`	Update an existing dedup rule set

`dedup_rule_set_membership`

Operation	Mega-tool	What it does
`create`	`entity_crud`	Create a new dedup rule set membership
`delete`	`entity_crud`	Delete a dedup rule set membership
`list`	`entity_crud`	List dedup_rule_set_memberships with filtering and pagination
`read`	`entity_crud`	Get detailed dedup rule set membership information
`update`	`entity_crud`	Update an existing dedup rule set membership

`document`

Operation	Mega-tool	What it does
`archive`	`document_op`	Archive a document by setting its status to 'archived'.
`bulk_status`	`document_op`	Update the status of multiple documents at once.
`chunk_retrieve`	`document_op`	Retrieve text chunks from a specific document for reading or RAG context assembly.
`classify`	`document_op`	Classify a document by applying classification rules to determine its type.
`create`	`entity_crud`	Create a new document
`create_viewing_room`	`document_op`	Bundle a curated list of documents into a shareable Viewing Room.
`delete`	`entity_crud`	Delete a document
`find_related`	`document_op`	Find documents related to an entity via DocumentLink.
`find_similar`	`document_op`	Find documents whose text chunks are similar to a reference document (text embeddings) — not pixels.
`get_transitions`	`workflow_action`	Get available transitions for a document
`image_text_search`	`document_op`	Find document images that VISUALLY match a free-text description (e.g.
`image_visual_search`	`document_op`	Find documents whose images look VISUALLY similar to a reference document's image (pixel features, not text descriptions).
`list`	`entity_crud`	List documents with filtering and pagination
`rag_status`	`document_op`	Get RAG pipeline health and indexing statistics for the organization.
`read`	`entity_crud`	Get detailed document information
`read`	`document_op`	Read a single document by UUID — returns full extracted_text, intelligence_summary, description, all metadata.
`reclassify`	`document_op`	Force reclassify a document, clearing existing classification before re-evaluating rules.
`reprocess`	`document_op`	Re-run the document processing pipeline: reset status to 'uploaded', clear the chosen processing outputs, then ENQUEUE the same Celery chain the REST…
`search`	`entity_crud`	Search documents by content and metadata.
`search`	`document_op`	Search documents by content using DocumentChunk text matching.
`search_guide`	`document_op`	Get the search strategy playbook for effectively finding information in the document library.
`semantic_search`	`document_op`	Semantic RAG search across ALL document chunks using vector embeddings.
`taxonomy_describe`	`document_op`	Describe the live v2 document-type taxonomy for the active organization.
`transition`	`workflow_action`	Transition document to a new status
`update`	`entity_crud`	Update an existing document

`document_analytics`

Operation	Mega-tool	What it does
`breakdown`	`report_query`	Get document analytics breakdown by dimension
`summary`	`report_query`	Document processing analytics and classification metrics
`trend`	`report_query`	Get document analytics trend over time

`document_chunk`

Operation	Mega-tool	What it does
`create`	`entity_crud`	Create a new document chunk
`delete`	`entity_crud`	Delete a document chunk
`list`	`entity_crud`	List document_chunks with filtering and pagination
`read`	`entity_crud`	Get detailed document chunk information
`update`	`entity_crud`	Update an existing document chunk

`document_classification_rule`

Operation	Mega-tool	What it does
`create`	`entity_crud`	Create a new document classification rule
`delete`	`entity_crud`	Delete a document classification rule
`list`	`entity_crud`	List document_classification_rules with filtering and pagination
`read`	`entity_crud`	Get detailed document classification rule information
`search`	`entity_crud`	Search document_classification_rules with fuzzy matching
`update`	`entity_crud`	Update an existing document classification rule

`document_import_job`

Operation	Mega-tool	What it does
`list`	`entity_crud`	List document_import_jobs with filtering and pagination
`read`	`entity_crud`	Get detailed document import job information
`search`	`entity_crud`	Search document_import_jobs with fuzzy matching

`document_label`

Operation	Mega-tool	What it does
`create`	`entity_crud`	Create a new document label
`delete`	`entity_crud`	Delete a document label
`list`	`entity_crud`	List document_labels with filtering and pagination
`read`	`entity_crud`	Get detailed document label information
`search`	`entity_crud`	Search document_labels with fuzzy matching
`update`	`entity_crud`	Update an existing document label

`document_link`

Operation	Mega-tool	What it does
`create`	`entity_crud`	Create a new document link.
`delete`	`entity_crud`	Delete a document link
`list`	`entity_crud`	List document_links with filtering and pagination.
`read`	`entity_crud`	Get detailed document link information
`search`	`entity_crud`	Search document_links with fuzzy matching
`update`	`entity_crud`	Update an existing document link

`document_relation`

Operation	Mega-tool	What it does
`create`	`entity_crud`	Create a new document relation
`delete`	`entity_crud`	Delete a document relation
`list`	`entity_crud`	List document_relations with filtering and pagination
`read`	`entity_crud`	Get detailed document relation information
`search`	`entity_crud`	Search document_relations with fuzzy matching
`update`	`entity_crud`	Update an existing document relation

`document_saved_view`

Operation	Mega-tool	What it does
`create`	`entity_crud`	Create a new document saved view
`delete`	`entity_crud`	Delete a document saved view
`list`	`entity_crud`	List document_saved_views with filtering and pagination
`read`	`entity_crud`	Get detailed document saved view information
`search`	`entity_crud`	Search document_saved_views with fuzzy matching
`update`	`entity_crud`	Update an existing document saved view

`document_source_config`

Operation	Mega-tool	What it does
`create`	`entity_crud`	Create a new document source config
`delete`	`entity_crud`	Delete a document source config
`list`	`entity_crud`	List document_source_configs with filtering and pagination
`read`	`entity_crud`	Get detailed document source config information
`search`	`entity_crud`	Search document_source_configs with fuzzy matching
`update`	`entity_crud`	Update an existing document source config

`document_type_definition`

Operation	Mega-tool	What it does
`create`	`entity_crud`	Create a new document type definition
`delete`	`entity_crud`	Delete a document type definition
`list`	`entity_crud`	List document_type_definitions with filtering and pagination
`read`	`entity_crud`	Get detailed document type definition information
`search`	`entity_crud`	Search document_type_definitions with fuzzy matching
`update`	`entity_crud`	Update an existing document type definition

`document_version`

Operation	Mega-tool	What it does
`create`	`entity_crud`	Create a new document version
`delete`	`entity_crud`	Delete a document version
`list`	`entity_crud`	List document_versions with filtering and pagination
`read`	`entity_crud`	Get detailed document version information
`search`	`entity_crud`	Search document_versions with fuzzy matching
`update`	`entity_crud`	Update an existing document version

`guide`

Operation	Mega-tool	What it does
`get`	`agent_command`	Org pipeline control playbook (two levels, subtract-only accounts, inheritance, source semantics, per-mailbox email lanes).
`query`	`report_query`	Documents agent playbook: where every documents id comes from and the order the workflows run in.

`import_job`

Operation	Mega-tool	What it does
`import_cancel`	`document_op`	Cancel a non-terminal bulk import job (org-scoped).
`import_items`	`document_op`	Per-file outcomes for a single bulk import job (org-scoped), ordered by sequence.
`import_list`	`document_op`	List this org's bulk import jobs, newest first.
`import_status`	`document_op`	Get the status, counts, and progress of a single bulk import job (org-scoped) by its id.
`import_submit`	`document_op`	Start a bulk document-import job from the org's pending staged uploads.

`pipeline`

Operation	Mega-tool	What it does
`infra_status`	`document_op`	Get read-only infrastructure / embedding health for the document pipeline: inline embedding-server health (HTTP /health probe + URL) and the GPU…
`pipeline_overview`	`document_op`	Get the evergreen corpus overview analytics for the organization: total documents, text/embed coverage percentages, the document->extracted->chunked and…
`pipeline_status`	`document_op`	Get the full live status of all 7 document-pipeline stages for the organization (SharePoint sync, email sync, text extraction, OCR, chunking, inline…

`pipeline_control`

Operation	Mega-tool	What it does
`get`	`config_manage`	Read one pipeline stage's control state (enabled + config) for the active org
`list`	`config_manage`	List every pipeline stage with its effective state, source, group and description
`reset`	`config_manage`	Delete a stage's control row for the active org, reverting it to the stage default
`set`	`config_manage`	Enable/disable a pipeline stage (and merge config) for the active org; busts the gate cache

`pipeline_stage`

Operation	Mega-tool	What it does
`run_chunking`	`smart_action`	Run-now the chunking stage org-wide (gated behind STUDIO_INLINE_STAGE_TRIGGERS, default OFF).
`run_email_sync`	`smart_action`	Run-now the email sync stage for this org: dispatch sync_all_email_accounts scoped to the current organization.
`run_embedding`	`smart_action`	Run-now the inline-embedding stage org-wide (gated behind STUDIO_INLINE_STAGE_TRIGGERS, default OFF).
`run_extraction`	`smart_action`	Run-now the text-extraction stage org-wide (gated behind STUDIO_INLINE_STAGE_TRIGGERS, default OFF).
`run_gpu_drain`	`smart_action`	Run-now the GPU batch-embedding stage for this org: dispatch drain_gpu_embeddings scoped to the current organization.
`run_ocr_sweep`	`smart_action`	Run ocr sweep pipeline stage.
`run_sharepoint_sync`	`smart_action`	Run-now the SharePoint/OneDrive sync stage for this org: dispatch a delta fan-out (run_scheduled_deltas) scoped to the current organization.

`search_settings`

Operation	Mega-tool	What it does
`get`	`config_manage`	Get the per-organization search-quality setting (DiskANN query-list-size); default 200 when unset
`set`	`config_manage`	Set the per-organization search-quality setting (DiskANN query-list-size, 50-500).

`share_point_dedup_manifest`

Operation	Mega-tool	What it does
`create`	`entity_crud`	Create a new share point dedup manifest
`delete`	`entity_crud`	Delete a share point dedup manifest
`list`	`entity_crud`	List share_point_dedup_manifests with filtering and pagination
`read`	`entity_crud`	Get detailed share point dedup manifest information
`search`	`entity_crud`	Search share_point_dedup_manifests with fuzzy matching
`update`	`entity_crud`	Update an existing share point dedup manifest

`share_point_operation`

Operation	Mega-tool	What it does
`list`	`entity_crud`	List share_point_operations with filtering and pagination
`read`	`entity_crud`	Get detailed share point operation information
`search`	`entity_crud`	Search share_point_operations with fuzzy matching

`share_point_saved_search`

Operation	Mega-tool	What it does
`list`	`entity_crud`	List share_point_saved_searches with filtering and pagination
`read`	`entity_crud`	Get detailed share point saved search information

`share_point_site`

Operation	Mega-tool	What it does
`create`	`entity_crud`	Create a new share point site
`delete`	`entity_crud`	Delete a share point site
`list`	`entity_crud`	List share_point_sites with filtering and pagination
`live_list_children`	`entity_crud`	LIVE SharePoint folder listing via Microsoft Graph (read-only GET).
`live_resolve_path`	`entity_crud`	Resolve a platform Document to WHERE IT ACTUALLY LIVES in SharePoint, live via Microsoft Graph (read-only GET).
`live_search`	`entity_crud`	LIVE SharePoint filename/content search via Microsoft Graph (read-only GET).
`read`	`entity_crud`	Get detailed share point site information
`search`	`entity_crud`	Search share_point_sites with fuzzy matching
`update`	`entity_crud`	Update an existing share point site

`source_connector`

Operation	Mega-tool	What it does
`crawl_status`	`smart_action`	Read sync state (sync_status, last_sync_*, last_sync_error) — use to poll a dispatched crawl.
`create`	`entity_crud`	Create a new SourceConnector (typically done by the discover command, but exposed for manual seeding)
`delete`	`entity_crud`	Delete a SourceConnector.
`list`	`entity_crud`	List SourceConnector rows (one per external drive/inbox) with filters and stats
`mark_sync_error`	`smart_action`	Force a connector into error state (for ops recovery, e.g.
`read`	`entity_crud`	Read a single SourceConnector including raw Graph metadata
`reset_sync_state`	`smart_action`	Clear delta_link, last_sync_error, and reset sync_status to 'never' so the next run is a full crawl.
`search`	`entity_crud`	Search SourceConnector by name/description/site/drive
`stats`	`smart_action`	Live aggregate stats from SourceRecord under this connector: counts by item_type/sync_status/extension, size sums.
`trigger_crawl`	`smart_action`	Dispatch a full Graph walk of the connector's drive via Celery.
`trigger_delta_sync`	`smart_action`	Dispatch an incremental Graph delta sync for one SharePoint connector via Celery.
`update`	`entity_crud`	Update a SourceConnector.

`source_record`

Operation	Mega-tool	What it does
`create`	`entity_crud`	Not supported — SourceRecord rows are created by the crawler via SourceRecord.from_graph_item.
`delete`	`entity_crud`	Soft-delete a SourceRecord (sets is_deleted=True).
`find_duplicates_by_hash`	`smart_action`	Group SourceRecord files sharing a content hash — the primary dedup signal.
`find_duplicates_by_name_size`	`smart_action`	Group SourceRecord files by (filename, file_size_bytes) — secondary dedup signal for items without a shared hash.
`link_to_document`	`smart_action`	Attach a SourceRecord to a Document by setting its document FK.
`list`	`entity_crud`	List SourceRecord rows (files/folders from external sources) with rich filtering
`list_empty_folders`	`smart_action`	List folder SourceRecords with child_count=0 — candidates for cleanup.
`read`	`entity_crud`	Read a single SourceRecord.
`search`	`entity_crud`	Search SourceRecord by filename/relative_path/description
`unlink_from_document`	`smart_action`	Clear the Document FK on a SourceRecord (does not delete the Document).
`update`	`entity_crud`	Update safe fields on a SourceRecord.
`verify_against_graph`	`smart_action`	Live path-GET against Microsoft Graph to confirm a SourceRecord still exists.

`staged_upload`

Operation	Mega-tool	What it does
`list`	`entity_crud`	List your OWN staged_uploads with filtering and pagination.
`list_pending`	`document_op`	List YOUR OWN PENDING staged uploads — the files you dropped on the /documents/staging Canvas that are awaiting action.
`promote`	`document_op`	Ingest a file into this organization's document library — the searchable document corpus — in ONE call and get back its document_id.
`pull_to_workspace`	`document_op`	Copy the raw BYTES of staged uploads onto your Studio seat's mounted workspace so you can read them as local files.
`read`	`entity_crud`	Get detailed information for one of YOUR OWN staged uploads.
`search`	`entity_crud`	Search your OWN staged_uploads with fuzzy matching.
`stage_from_bytes`	`document_op`	Stage a single local file for import by pushing its bytes directly over MCP (no multipart REST round-trip).

`taxonomy_audit_event`

Operation	Mega-tool	What it does
`list`	`entity_crud`	List taxonomy_audit_events with filtering and pagination
`read`	`entity_crud`	Get detailed taxonomy audit event information
`search`	`entity_crud`	Search taxonomy_audit_events with fuzzy matching

`taxonomy_draft`

Operation	Mega-tool	What it does
`create`	`entity_crud`	Create a new taxonomy draft
`delete`	`entity_crud`	Delete a taxonomy draft
`list`	`entity_crud`	List taxonomy_drafts with filtering and pagination
`read`	`entity_crud`	Get detailed taxonomy draft information
`update`	`entity_crud`	Update an existing taxonomy draft

`taxonomy_snapshot`

Operation	Mega-tool	What it does
`create`	`entity_crud`	Create a new taxonomy snapshot
`delete`	`entity_crud`	Delete a taxonomy snapshot
`list`	`entity_crud`	List taxonomy_snapshots with filtering and pagination
`read`	`entity_crud`	Get detailed taxonomy snapshot information
`search`	`entity_crud`	Search taxonomy_snapshots with fuzzy matching
`update`	`entity_crud`	Update an existing taxonomy snapshot

`template`

Operation	Mega-tool	What it does
`archive`	`document_op`	Retire a template: set its status to archived.
`create`	`document_op`	Create template.
`duplicate`	`document_op`	Fork a template into a new DRAFT in the same organization — source, schema, tokens and every image asset copied.
`list`	`document_op`	List the Typst document templates THIS organization can render — the answer to "what documents can you produce for me?".
`read`	`document_op`	Read template.
`render`	`document_op`	Render a template to a real PDF and file it in the organization's document library.
`seed_house_templates`	`document_op`	Install the platform's shipped house templates (branded-report, legal-instrument, customer-deliverable) into THIS organization.
`update`	`document_op`	Patch an existing template.
`validate`	`document_op`	Dry-run a template: substitute the variables, compile it with Typst, and report what happened WITHOUT writing anything — no library document, no render row…

`template_asset`

Operation	Mega-tool	What it does
`create`	`document_op`	Upload an image a template's Typst source references by name.
`delete`	`document_op`	Remove an image asset from a template.
`list`	`document_op`	List the image assets a template carries — the files its Typst source can reference by name, e.g.

`template_render`

Operation	Mega-tool	What it does
`read`	`document_op`	Read one template render — its status (pending/running/succeeded/failed), how long it took, the error log if it failed, and the library document it produced.

`template_revision`

Operation	Mega-tool	What it does
`list`	`document_op`	List a template's version history, newest first.
`read`	`document_op`	Read one frozen revision in full — the exact typ_source, variable_schema and brand_tokens the template carried at that version.
`restore`	`document_op`	Put an earlier revision's content back on the template.

`valve`

Operation	Mega-tool	What it does
`create`	`entity_crud`	Create a new valve
`delete`	`entity_crud`	Delete a valve
`list`	`entity_crud`	List valves with filtering and pagination
`read`	`entity_crud`	Get detailed valve information
`search`	`entity_crud`	Search valves with fuzzy matching
`update`	`entity_crud`	Update an existing valve

`valve_photo`

Operation	Mega-tool	What it does
`create`	`entity_crud`	Create a new valve photo
`delete`	`entity_crud`	Delete a valve photo
`list`	`entity_crud`	List valve_photos with filtering and pagination
`read`	`entity_crud`	Get detailed valve photo information
`search`	`entity_crud`	Search valve_photos with fuzzy matching
`update`	`entity_crud`	Update an existing valve photo

`version`

Operation	Mega-tool	What it does
`create_version`	`document_op`	Create a new version of a document.
`list_versions`	`document_op`	List all versions of a document, ordered by creation date (newest first).
`restore_version`	`document_op`	Restore a document to a previous version.

`viewing_room`

Operation	Mega-tool	What it does
`create`	`entity_crud`	Create a new viewing room
`delete`	`entity_crud`	Delete a viewing room
`list`	`entity_crud`	List viewing_rooms with filtering and pagination
`read`	`entity_crud`	Get detailed viewing room information
`search`	`entity_crud`	Search viewing_rooms with fuzzy matching
`update`	`entity_crud`	Update an existing viewing room

`viewing_room_folder`

Operation	Mega-tool	What it does
`list`	`entity_crud`	List viewing_room_folders with filtering and pagination
`read`	`entity_crud`	Get detailed viewing room folder information

Parameter schemas and permission codenames are in the full reference — sign in — or call prism_introspect(dimension="capability_search", query="…") with your key.

In the full reference this application appears under agent_command, config_manage, document_op, entity_crud, report_query, smart_action, workflow_action.

Documents

access_grant

access_scope

attachment

dedup_rule

dedup_rule_set

dedup_rule_set_membership

document

document_analytics

document_chunk

document_classification_rule

document_import_job

document_label

document_link

document_relation

document_saved_view

document_source_config

document_type_definition

document_version

guide

import_job

pipeline

pipeline_control

pipeline_stage

search_settings

share_point_dedup_manifest

share_point_operation

share_point_saved_search

share_point_site

source_connector

source_record

staged_upload

taxonomy_audit_event

taxonomy_draft

taxonomy_snapshot

template

template_asset

template_render

template_revision

valve

valve_photo

version

viewing_room

viewing_room_folder

Parameter schemas and permissions