Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already flag destructiveHint=true and idempotentHint=false, and the description adds genuinely useful scope: the draft is not sent or published, uploaded originals are immutable through this tool, and entryIds must reference owned experience. These are ownership, mutation-scope, and workflow facts the annotations cannot express. It does not say what happens to a prior revision when overwritten, which is the remaining gap.

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?

Four short sentences, front-loaded with the create-or-revise action, then edit mechanics, then the non-publishing boundary. Dense with no filler. The content-quality instruction ('use confirmed facts only') sits slightly awkwardly between action and parameter guidance but is worth its space.

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?

For a six-parameter, destructive, output-schema-less mutation tool, the description covers the risky parts well: edit identity via documentId+revision, immutability of uploads, and ownership of entryIds. It is silent on what a successful save returns (e.g. new revision token) and on how name/document_type interact with an existing draft, which an agent would need in order to chain a follow-up edit.

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 description coverage is 0%, so the description carries the burden. It usefully explains the documentId/revision pairing for edits and the ownership requirement on entryIds, but leaves name, html (100k length cap), and the document_type enum values entirely to the schema. That is real added meaning for 2 of 6 parameters, not full compensation.

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?

The description opens with a specific verb pair and resource: 'Create or revise a generated HTML document for the connected user to review.' That clearly separates the create path from the edit path and distinguishes the tool from read-side siblings like get_document and list_documents. It stops short of naming a sibling explicitly, so an agent must infer the boundary with render_document on its own.

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?

Concrete when-to-use conditions are given: supply documentId plus the current revision to edit, and note that uploaded originals cannot be edited. It also sets content expectations (confirmed facts only, label missing information) and clarifies the tool does not send or publish. No alternative tool is named for the read or render case, which keeps it below a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.