proof_review

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

Annotations only give the generic flags (readOnlyHint=false, destructiveHint=false, idempotentHint=false); the description adds real behavioral context by stating the review is recorded against 'immutable' revision-bound report URIs and that it 'Does not alter font sources or assert human approval,' which sets expectations about side effects and scope of authority. It omits that repeat calls are non-idempotent (new records), which the annotations imply.

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?

Three tight sentences, front-loaded with the core action, then verdict rules, then the boundary statement. No filler; every sentence carries information, though the final two clauses are slightly compressed and could read ambiguously.

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 non-read-only recording tool with an output schema present, the description covers the precondition (inspect images first), the verdict-dependent requirements, and what it does not do (no font-source mutation, no human approval claim). It is nearly complete, with only the non-idempotent recording behavior and observation input constraints unaddressed.

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 does explain the verdict semantics and the finding_id/reason requirement for resolutions, and ties proof_uris and revision together ('immutable render report_uris from an exact revision'). However, project_id, observation, and the array/length constraints (maxItems 8, minLength 12/20, hex patterns) are left entirely to 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?

The description states a specific verb and resource: 'Record an agent's visual review of immutable render report_uris from an exact revision.' This clearly separates it from siblings like render_proof or font_validate, though it never names an adjacent tool explicitly, so an agent must infer the pairing with render_proof.

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 actionable conditions: 'Use verdict=revise for defects', 'accepted intentional findings require their finding_id and a reason', and the precondition 'Inspect actual images before calling.' That is clear when-to-use guidance, but there is no exclusion (e.g., when not to use this versus re-rendering the proof) and no mention of alternatives.

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