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

Goes well beyond the readOnlyHint annotation by disclosing sorting by completeness, scroll_token pagination, a credit cost per returned record, the API endpoint, and the two supported query languages. An agent can anticipate the operation's side effects and response 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?

Each sentence adds a distinct fact: what it searches, how to query, return/pagination behavior, cost, and API route. The most important capabilities are front-loaded, and there is no filler.

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 an 8-parameter, no-output-schema tool, the description covers query selection, pagination, result ordering, and cost. It stops short of describing the actual response fields or the tradeoffs between sql and query, but the schema and context signals cover the remaining parameter-level detail.

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 schema already covers all 8 parameters, but the description adds the crucial relationship that sql and query are alternative modes (OR), clarifies pagination via scroll_token, and frames the search as over the Person Schema. This is meaningful value beyond the individual property descriptions.

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 an explicit action — search the full PDL Person Dataset — plus the two query modes (Elasticsearch query object or SQL string). This makes the tool's scope immediately distinct from siblings like pdl_person_enrich and pdl_person_identify, even though it doesn't name them.

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 clearly conveys general context (full-dataset search via query or SQL, pagination, credit cost) and implies it is for searching rather than enriching or identifying a known person. However, it never explicitly states when to prefer this tool over person_enrich or person_identify, nor does it give exclusions or alternative conditions.

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