search_experts

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

Annotations already indicate read-only, idempotent, and open-world behavior, but the description adds significant behavioral context: it explains that evidence is provided for each match, that OpenAlex topics are 'lower-priority, clearly labeled evidence,' that general biographies are excluded, and that exhaustive results require following next_offset while has_more. This goes well beyond the annotations and fully discloses the tool's behavior.

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 three sentences, front-loaded with the primary purpose, then adding scoping, exclusions, and pagination. Every sentence adds distinct value with no redundancy or filler. The structure is tight and easy to parse.

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 presence of an output schema, the description does not need to explain return values. It covers what is searched, what is excluded, a conditional behavior, a parameter constraint, and pagination. For a read-only search tool with annotations covering safety, this is complete. Nothing an agent needs to call it correctly is missing.

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 compensate. It clarifies the 'unit' parameter ('must be an exact ID') and implies the use of offset/limit through the pagination instruction. However, it does not explain the 'query' parameter semantics or the 'limit' parameter's effect/range. While query and limit are reasonably intuitive, the description does not fully cover all four parameters, leaving some burden on the schema-less definition.

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 opens with a specific verb and resource: 'Find active researchers and explain the evidence for each match.' It then enumerates the searched sources (curated expertise, research interests, research profiles, OSIRIS topics) and explicitly excludes 'General biographies,' which distinguishes it from sibling tools like search_people. An agent can clearly identify what this tool does and how it differs from similar search tools.

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 gives clear boundaries: 'General biographies are not searched' and notes the conditional inclusion of OpenAlex topics when Spectrum is enabled. It also provides operational guidance on unit being an exact ID and pagination via next_offset/has_more. While it does not explicitly name alternative tools, the negative scoping and conditional behavior effectively guide when to use this tool. Missing explicit alternatives prevent a 5.

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