Available tools

​

Knowledge

• search_knowledge (read): hybrid vector and full-text search over the workspace knowledge base, returning ranked excerpts.
• ask_knowledge (read): a synthesized answer to a question, with cited sources.

​

Folders

• list_folders (read): the folders you can open — top level, by name, or one folder’s path, subfolders, sessions and document count. Its documents come from list_documents folder_id.

​

Documents

• list_documents (read): the documents and pages you can reach, filtered by folder or library section, with your role on each.
• read_document (read): a document as markdown, windowed for long content, always with its version.
• create_document (write): a new document in a session, a conversation or your library, optionally pre-filled, with idempotent retries.
• edit_document (write, destructive): append, replace a quoted section, replace everything, or fill an empty document while people may be editing it live.
• get_document_versions (read): the recent checkpoints and named versions, newest first.
• archive_document (write, idempotent): archive a document, page or table so it leaves listings and refuses edits, or restore it. Nothing is deleted.

​

Pages

• create_page (write): a new HTML page artifact in a conversation or your library.
• read_page (read): a page’s stored HTML and its version.
• write_page (write, destructive): replace a page’s HTML under a required expected_version; a conflict returns a diff.

​

Automations

• list_automations (read): the automations you can see — personal and workspace — with trigger, state and whether you may change each.
• read_automation (read): one automation’s steps, writes, trigger and version; include_plan for its plan JSON, include_runs / run_id for its history.
• describe_capabilities (read): the vocabulary for writing a plan — connected systems, node shapes, bindings, triggers and the capability catalogue per namespace.
• draft_automation (write): a plan JSON in, a validated draft out — or every error by rule and path.
• edit_automation (write): publish a draft behind a trigger, run it (or dry_run), set_enabled to pause or resume. No delete.

​

Export

• export_document (read): render a document, page or table to markdown, PDF, HTML, CSV or JSON and get a 15-minute download URL.

​

Uploads

• request_upload_url (write): a single-use URL to curl a large markdown or HTML file to, then pass its upload_id to a document or page write instead of the content.

​

Comments

• read_comments (read): the comment threads on a document or page, with anchors, replies and your role.
• add_comment (write): start a thread, optionally anchored to a quoted passage, or reply in one.
• resolve_comment (write, idempotent): resolve or reopen a thread.

​

Resources

• sidecars://document/{id}: the documents you can reach, as text/markdown resources for hosts that mount them next to tools.

​

Which methods need a token

​

How to read a tool result

{
  "content": [{ "type": "text", "text": "Created \"Q3 launch plan\" (document_id: k97fq2example000000000000000000, version 1)." }],
  "structuredContent": {
    "document_id": "k97fq2example000000000000000000",
    "title": "Q3 launch plan",
    "version": 1
  }
}

​

Not exposed

• Posting messages or reading a session’s messages (list_folders lists a folder’s sessions by title only).
• Sharing, granting, moving or linking artifacts.
• Restoring a version, naming a version, or deleting anything (archive_document retires an artifact reversibly; nothing is ever removed).
• Editing tables (a table is filled in by the agent that created it).
• Resource subscriptions (notifications/resources/updated).
• Prompts (prompts/list is answered as unsupported).