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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description is free to add operational behavior — pagination, the returned proposal_version and can_amend fields, and the version-pinning rule for stable paging. 'Pending content is not published knowledge' is a genuinely useful disclosure about the nature of the content, though return shape details (beyond two fields) remain unstated.

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 default behavior, then the alternate view, then return fields, then the paging constraint. No filler and every clause is actionable.

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 an 8-parameter read tool with no output schema, it covers the primary modes, the key returned fields, and the paging contract, which is most of what an agent needs. The remaining gap is the under-specified paging parameters (limit_chars, result_offset, offset), which materially affect large reads.

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% across 8 parameters, so the description carries the burden. It explains view, document_id, proposal_version, and implies pagination, but leaves limit_chars, result_offset, and the distinction between offset and result_offset completely unaddressed, so an agent must guess at two similarly named paging parameters.

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 names a specific verb and resource ('Read a proposal') and goes further by spelling out the two modes: a default paginated unified diff, and 'view=proposed with document_id' for the full proposed text. It does not explicitly contrast itself with near siblings like read_document or list_changes, which keeps it from a 5.

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?

It gives clear triggering context for each mode ('by default' vs 'view=proposed with document_id') and an operational instruction ('Pin proposal_version when paging'). It stops short of explicit exclusions or naming the sibling tool to use instead when you want published documents rather than proposals.

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