audit_findings_validate

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

No annotations are supplied, so the description carries the full behavioral burden. It discloses a validation rule (needs-validation records cannot carry severity) but never says whether the tool reads or mutates the records, what happens when validation fails, or how results are surfaced — critical for a tool named 'validate' with no annotation hints.

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-loaded with the phase and the validation targets, with the constraint sentence second. No filler or redundant restatement of the tool name.

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?

With no output schema and no annotations, the description should say what a validation call returns (counts of invalid records, error list) and whether it aborts on first failure. It covers scope and one rule but leaves the return behavior and failure mode undefined.

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?

There is one parameter at 0% schema description coverage and the item schema is an empty object, so the schema conveys nothing about record shape. The description partly compensates by naming the fields validated (structure, evidence, fingerprints) and the maxItems cap is visible in schema, but the required record format remains undocumented.

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 (validate) and enumerates the concrete aspects checked: finding structure, evidence fields, and unique fingerprints. The 'Phase 4' prefix signals pipeline position. It does not distinguish this from sibling validators such as audit_coverage_validate or cloudflare_findings_validate, so it stops short of a 5.

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?

'Phase 4' implies this runs after earlier audit phases, which is useful implied ordering, and the severity rule gives one actionable constraint. There is no explicit when-not guidance and no reference to the sibling validation tools, so the agent must infer which validator applies.

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