evidence_verify

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it delivers substantial detail. It reveals that self-attested collection, unsigned bundles, and unverifiable controls all surface as findings, and that 'unknown' observations remain unreviewed rather than counting as enforced. This goes beyond a generic summary and gives the agent accurate expectations for how edge cases are handled.

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 description is appropriately sized and well-structured, opening with a one-line summary then providing behavioral details and an Args section. Every sentence adds value, and there is no redundant or filler content. The formatting makes it easy to scan for key information.

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?

Given the tool's moderate complexity, the description covers all necessary aspects: the action, the input format, the behavioral quirks, and the output categories. An output schema exists, so return structure is handled separately. The description is complete enough for an agent to select and invoke the tool correctly, leaving no significant gaps.

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?

The input schema provides no descriptions for the two parameters (0% coverage), so the description is the sole source of meaning. It adds essential context: bundle_json must be a 'cinch-evidence/1' bundle as returned by evidence_collect, and deployment is an optional override. This enables correct invocation despite the schema being empty.

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 opens with a specific verb 'Grade' and a clear resource ('an evidence bundle'), then enumerates the outputs: score, letter grade, insights, recommendations, plan. This distinguishes it from sibling tools like evidence_collect (which gathers bundles) and checklist_run (which executes checklists), leaving no ambiguity about its function.

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 tool's usage context is clear: it is meant for grading evidence bundles, and the input is explicitly tied to the output of evidence_collect. The description also states it applies the same rubric a human reviewer sees, which signals when it is appropriate. However, it does not explicitly exclude other tools or mention when not to use it, so it falls short of an explicit when-to-use versus alternatives.

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