Check candidate result

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

No annotations are present, so the description carries the full burden. It discloses the separation-of-duties rule, the non-claiming invocation pattern, and the state effect of rejection. It does not explain success behavior or idempotency, but the core behavioral traits are covered.

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 concise sentences, each adding value: action, constraint, outcome. No fluff, well front-loaded, and easily scannable.

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 tool has 7 parameters and state-changing behavior, but the description omits critical details like approval outcomes, idempotency semantics, expectedVersion usage, and the role of notes/evidence. It is not sufficient for an agent to fully predict the tool's behavior.

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 schema description coverage at 0%, the description must compensate, but it only indirectly references taskId (as 'review_target_task_id') and approved (via 'Rejection'). The remaining parameters (reviewerId, expectedVersion, notes, evidenceRefs, idempotencyKey) are not explained, failing to add meaningful semantics.

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 clearly states the action ('Independently check a candidate') and provides a resource context. It distinguishes from submission tools by emphasizing an independent review, but it does not explicitly contrast with the sibling 'result_verify' tool, leaving some ambiguity.

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 gives a concrete usage scenario: 'Luna verifiers call this on review_target_task_id without claiming.' It also specifies the reviewer/producer separation constraint. It lacks an explicit 'use this instead of X' exclusion but otherwise offers actionable context.

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