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

Beyond annotations that already declare read-only/idempotent/non-destructive, the description adds substantive behavioral context: matches are deterministic, and the response includes evidence, caveats, and blocked lifecycle states. It also clarifies what the tool does not do (outreach, conversion, import, AI ranking), giving the agent a realistic expectation of the tool's boundaries.

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 concise and front-loaded with the primary purpose, then adds scope constraints efficiently. The 'Read-only' clause is redundant given the annotations, but it is not distracting. Overall, every sentence earns its place with minimal waste.

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?

The description covers the core purpose and exclusion scope well, but with no output schema it does not describe the response format, pagination, or ordering. The request_id parameter is left ambiguous, and the meaning of 'evidence, caveats, and blocked lifecycle states' is only hinted at. The tool is callable with a job_id, but an agent cannot fully anticipate the return structure.

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?

The description implies that job_id identifies the job being matched but provides no detail on the request_id parameter. With 0% schema coverage, request_id remains completely unexplained, and even job_id lacks format or example context. The description fails to compensate for the sparse schema.

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 uses a specific verb ('List') and a specific resource ('deterministic Talent CRM prospect matches for one Job'), which immediately distinguishes it from generic lists like prospects_list or applications_list. Mentioning 'Talent CRM' and 'for one Job' leaves no ambiguity about what the tool targets.

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 contextual guidance by enumerating exclusions ('without outreach, conversion, import, or AI ranking'), which implicitly conveys that this tool is not for initiating actions or AI-ranked results. However, it does not explicitly name alternative sibling tools or state when to prefer one over the other.

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