Update a document's title, body, placement, attachments, or portal visibility by sending only the fields you want to change. Use it to move, archive, restore, star, or publish documents.
Updates a document's title, body or placement. Send only the fields you want to change.
| Name | Required | Description | Default |
|---|---|---|---|
| body | Yes | Partial update of a document. Every field is optional; an omitted or null field is left as it is. | |
| documentId | Yes | Document to update. |
Changes observed during successful MCP inspections.
v1.1.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false), so the bar is lower, and the description does add the meaningful partial-update contract (omitted/null fields are left unchanged). But it omits the cascading effects that matter most — archiving a document archives every descendant at any depth, and an empty Attachments array removes all attachments — which sit uneasily against destructiveHint=false. The description could have surfaced that tension; the schema carries it instead.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two tight sentences with the verb and scope front-loaded and no filler. It is slightly under-sized for a tool with ten optional nested fields and cascading archive semantics, so conciseness shades into thinness, but nothing written is wasted.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The nested body schema is unusually rich, so per-field detail need not be repeated in prose. Still, for a mutation tool with no output schema and no annotation detail beyond two booleans, the description should have signaled the destructive-capable operations and versioning behavior; leaving them buried in property text risks an agent calling it without realizing archiving is recursive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The description earns above baseline by clarifying a genuine ambiguity the schema creates: both documentId and body are required, yet body's members are all optional, and 'send only the fields you want to change' tells the agent it must pass body but may leave members out.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a clear verb+resource (updates a document) and correctly separates it from create/duplicate/get siblings. However the enumerated scope — 'title, body or placement' — covers only three of the schema's capabilities; the tool can also archive/restore sub-trees (StatusId), star, replace attachments, set AlternateName, and toggle public link / portal publishing. An agent reading only the description would badly underestimate what this tool does.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
'Send only the fields you want to change' is invocation guidance, not usage guidance; it never says when to choose this over gorelo_create_document, gorelo_duplicate_document, or gorelo_restore_document_version, and names no alternatives or preconditions. The reader must infer that this is the general-purpose edit path.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.