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

Annotations only declare readOnlyHint/openWorldHint; the description goes far beyond by disclosing that comment marks are deliberately stripped, that absent fields mean "could not be asked" rather than "none", that `warnings` names lossy format conversions, and that the text is canonical round-trippable Markdown with specific escaping rules. This is exactly the behavioral context annotations cannot carry.

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?

Front-loaded with the core purpose, then layers the nuances in descending importance. It is dense and occasionally rambling (the version aside, the parenthetical escaping example), but nearly every clause carries information an agent would otherwise get wrong.

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?

No output schema exists, so the description carries the full burden of describing return values — and it does, field by field, including the purpose of `url` versus `title` and the meaning of missing fields. Nothing material needed to call or interpret the result is missing.

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% and both parameters are fully documented there, so the baseline is 3. The description references documentId only incidentally via list_comments({documentId}) and never mentions expectedProjectId or its cross-project targeting/refusal semantics, adding nothing beyond the schema.

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?

Opens with a specific verb+resource and scope ("Reads ONE document in full") and then enumerates exactly what is returned: Markdown text, language, anchor block, version, attachment metadata, and comment counts. An agent can distinguish it from get_document_revision, list_documents, and update_document without opening any schema.

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?

Gives concrete routing: non-zero `comments` means use list_comments({documentId}); the version field is flagged as the value update_document expects. It lacks explicit guidance on when to prefer get_document_revision or list_documents over this tool, but the positive usage contexts are clear.

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