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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds non-annotation context: a hard 10-claim ceiling, the paid-tier escape hatch with its endpoint, and the distinction that locale affects only human-localized module availability while canonical identifiers stay language-independent.

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 sentences, front-loaded with the core action and its output shape, then limits, then the locale nuance. Dense but every clause carries information; only the premium-tier sentence borders on tangential for an agent deciding whether to call this tool.

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, the description compensates by enumerating the returned bundle fields (statements, verdicts, review dates, evidence pointers, canonical URLs, clinical-state pin). Combined with the 10-claim limit and premium-tier note, an agent has everything needed to call it 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 0%, so the description must carry the load, and it does: it identifies claim_ids and query as alternative resolution inputs and explains locale as a BCP-47 code controlling human-localized module availability. It does not clarify whether query and claim_ids are mutually exclusive or how they interact, leaving one 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 (resolve) and resource (claims into an evidence bundle), and enumerates the bundle contents (statements, verdicts, review dates, evidence pointers, canonical URLs, clinical-state pin). This clearly distinguishes it from siblings like get_claims and get_evidence_log, which do not bundle verdicts and review dates together.

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?

Explains the two accepted input modes (claim_ids or free-text query) and names the boundary condition for the alternative: bulk export beyond 10 claims goes to the paid tier at /api/premium/evidence-pack. It does not explicitly say when to prefer this over get_claims or get_evidence_log, 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.