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

Annotations already declare non-read-only, open-world, idempotent, non-destructive, so the safety surface is partly covered; the description usefully adds the 2-hour hold, that repeat calls renew it, and that the call returns the bot's brief with instructions and rules. The final line about contributor-only posting is cryptic and reads as an access/visibility note rather than an actionable constraint, and no failure modes or prerequisites (e.g. what if no bot request exists) are described.

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?

The size is appropriate and it front-loads the verb, but the middle clause ('answers its brief with what the bot asks, where to work and the rules') is grammatically tangled and takes effort to parse, and the closing sentence about contributors checking gitranks.com is unclear about its relevance to the caller.

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?

With no output schema, the description correctly explains what the call yields (the bot's brief: what it asks for, where to work, and the rules) plus the hold duration and renewal behavior. For a two-parameter state-creating tool this is close to sufficient, with only error/prerequisite behavior left implicit.

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 100%, covering the 'pr' format (owner/repo#123 or URL) and the nested agent object with an enumerated name and free-text model. The description adds nothing about either parameter, which is acceptable given the schema does the work, but no value is added.

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 specific verb and resource ('Starts a proof on one of your pull requests') and narrows the scope with a precondition ('whose review bot asks for real behavior proof'), which concretely identifies the situation. It never names the obvious downstream siblings (finish_proof, submit_proof), so an agent must infer the workflow handoff, but the action itself is unambiguous.

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 a clear trigger condition (a review bot requesting real behavior proof) and a repeat-use rule ('Calling again renews the hold'). It stops short of saying when NOT to use it or pointing to finish_proof/submit_proof as the next step, so the workflow transition is implicit rather than explicit.

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