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

The readOnlyHint annotation already establishes that this is a non-mutating lookup, so the bar is lower. The description adds genuine behavioral context beyond the annotations: results are constrained to public or literature disclosures, each row is attributed to either the provider's own public claim or a literature disclosure, and the payload is deliberately terse with fuller evidence deferred to the public finder page. It does not discuss result limits, ranking, or what an empty result means.

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 short and front-loaded with the resource definition before the caveats. The clipped phrasing ('No DOIs, no sentences') is efficient but slightly telegraphic, and the return-shape note partially repeats what the output schema already conveys. No sentence is wasted.

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 one-parameter read-only lookup with full schema coverage and an output schema, the description carries adequate weight: it defines the entity, the evidence split, and the terse-payload expectation. It is only marginally complete on usage routing and edge cases such as unavailable or ambiguous proteins.

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 a single parameter with 100% schema description coverage, and the schema already states it accepts a protein symbol or alias with an example (KRAS). The description adds no further meaning about accepted aliases, case sensitivity, or ambiguity handling, so the baseline of 3 applies.

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 names the specific resource (CROs) and the qualifier that defines the result set: providers with publicly disclosed or literature-disclosed work for a given protein, plus whether the evidence is a provider claim or a literature disclosure. That distinguishes it cleanly from find_protocol and find_supplier, which return different entities. The verb is only implied by the tool name rather than stated in the text, which keeps it just 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?

There is no explicit statement of when to use this tool versus find_supplier or find_protocol, and no stated preconditions (e.g. what to do when a protein alias is ambiguous, or whether it is limited to disclosed evidence only). The phrase 'No DOIs, no sentences' sets a scope expectation for output but is not usage guidance. An agent must infer the selection rule from the resource name alone.

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