audit_claims

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

With no annotations provided, the description carries full burden. It clearly states the tool returns validity, support-level distribution, orphan evidence references, and unsupported-claim counts. It also explicitly declares what it does not do (verifying truth or source reputation). It does not mention destructive actions or authentication needs, but the non-destructive nature is implied by 'returns' statements.

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 compact with four sentences, each serving a distinct purpose: stating the core action, usage context, input requirement, and output summary with a limitation. No redundant 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 single parameter, lack of output schema, and annotations, the description covers all necessary aspects: what the tool does, when to use it, what input to provide, what it returns, and its limitations. It is fully adequate for the agent to use correctly.

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 100%, and the description adds significant meaning beyond the schema: it specifies that audit_json should match evidence-audit.schema.json, which guides the agent on expected structure. This is a crucial detail not present in the schema's description.

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 tool validates a claim-level evidence audit and summarizes support quality. It specifies the resource (claim-level evidence audit) and the action (validate and summarize), distinguishing it from sibling tools like validate_brief and validate_evidence which likely operate on different scopes.

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 explicitly says when to use the tool ('after drafting or receiving a memo to check whether important claims point to evidence IDs...') and what it does not do ('does not verify factual truth or source reputation'), providing good guidance on appropriate contexts. However, it does not explicitly name alternative tools for different scenarios, which would strengthen the guidance.

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