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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely non-obvious context: 'It cannot see your machine; it checks structure and consistency only' and 'Returns verdicts and an updated token', which sets correct expectations about the validator's limits and its token-mutating side effect.

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 with no filler; each carries distinct information (when to use, what is validated, what it cannot do and what it returns). The usage instruction is front-loaded ahead of the purpose statement, which slightly delays the 'what it does' answer.

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 two-parameter validator with a nested evidence array and no output schema, the definition covers the trigger, the scope of validation, the limitation (no machine access), and the return shape. Enough to call it correctly, though per-kind evidence semantics (e.g. which fields each 'kind' requires) are left to the schema.

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 coverage is 50%, and the description compensates partially by naming the evidence dimensions checked (exit codes, test counts in output, hashes, URL status, evidence level), which maps roughly onto exit, passed/failed, out, sha256, url, and kind. It does not explain the token parameter's lineage or the item ID pattern (^AC[0-9]{2}$) and required fields beyond what the schema already states.

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: 'Validates one to four evidence records against DoD items in the contract token', and enumerates what is checked (exit codes, test counts, hashes, URL status, evidence level). It never names a sibling such as check_flow_done, so the boundary with the adjacent tools is implied rather than stated.

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?

'Use after running a check' gives a clear triggering condition and the definition implies a lifecycle position (start -> run -> check evidence). No explicit when-not-to-use case or named alternative is provided, so it stops short of full routing guidance.

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