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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's value lies in what it adds: an explicit scope limitation (no truth verification) and a data-handling restriction to public/synthetic input. That is meaningful behavioral context beyond the annotations. It still says nothing about output form or whether findings are returned as a list of issues.

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, no filler, and the scope constraint is placed immediately after the statement of purpose. The terseness costs some clarity but every word earns its place.

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?

Safety behavior is covered by annotations, but for a tool that accepts an arbitrary nested object with no schema documentation and returns no output schema, the description leaves too much undefined: expected record shape, what an 'audit' result looks like, and what happens to non-public input. It is minimally usable but not complete.

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 required nested-object parameter ('record') with 0% schema description coverage, and the description never names it or explains what the object must contain. The phrases 'evidence references, qualifiers and commitments' may correspond to fields inside the record, but this is only a hint. With the schema carrying no documentation, the description does not compensate for the coverage gap.

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 ('Check') and the precise objects of inspection: declared evidence references, qualifiers and commitments. That is more informative than a generic 'audit' label. No sibling differentiation is offered, but none of the listed siblings (read_*, submit_*, report_*) overlaps this function, so the gap is minor.

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 clause 'Does not verify truth' functions as a when-not boundary, and 'public or synthetic input only' scopes acceptable input. However, no alternatives or positive trigger conditions ('use this when you have a submitted draft with cited evidence') are given, leaving the agent to infer when to reach for this tool versus read_draft_status or report_content.

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