review

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false; the description's 'never edits files' reinforces but does not substantially extend them. It adds the input scope and output signal names, but no details about auth, side effects, or failure modes.

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?

Two short sentences front-load the core purpose and the critical safety guarantee. Every clause contributes useful information with no filler.

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?

The output schema exists, so return-value details are not required, but the tool has five parameters including nested objects and thresholds with defaults. The description provides no guidance on structuring 'state' or 'checks' or interpreting 'pass_at' and 'review_at', making it incomplete for correct invocation.

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?

With 0% schema description coverage, the description must carry parameter meaning, but it only glosses 'against checks' and implies that 'state' is a diff/plan/test report. The 'model', 'pass_at', and 'review_at' parameters and their meanings are left completely unexplained.

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 clear verb ('Evaluate'), specific inputs ('a diff, plan, or test report'), and distinct outputs ('pass/review/fail signals'). It is unambiguous, though it does not explicitly distinguish itself from sibling evaluator-style tools like 'evaluate', 'check', or 'verify'.

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?

The description implies when to use it: when a diff, plan, or test report needs to be checked against evaluation criteria. It provides no explicit alternatives, when-not-to-use guidance, or comparison with the sibling tools, so the agent must infer routing.

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