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

Annotations already cover read-only, idempotent, non-destructive, and closed-world, so the description's added value is real: it discloses ordering ('newest first'), what the records contain (contact details, job, pipeline stage), and that results default to active candidates unless archived ones are requested via include_archived. It does not discuss pagination limits or that cursor errors behave, which keeps it from a 5.

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?

Two tight sentences: the identification and result shape come first, the search/filter modes second. Every clause carries information and nothing is repeated.

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 takes on the job of describing the returned shape and does so (contact details, job, stage, ordering), and the six parameters are fully covered by the schema. Pagination behavior is only implicit in the curated cursor parameter, a minor gap for a listing tool.

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 100%, so each parameter is already documented with defaults, bounds, and enum values. The description reinforces query and the two filter dimensions but adds no syntax, matching behavior, or default-page-size detail beyond the schema, so the baseline 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 uses a specific verb and resource ('Find candidates (applications)') and clarifies the result ordering, returned fields, and the two search modes (text query vs. job/stage filtering). It is clearly distinguishable from list_jobs and get_candidate, though it never names a sibling to route the agent away from.

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?

It explains how to use the tool ('Search by name, email or headline; filter by job or stage group'), which implies the search-vs-listing choice, but gives no explicit when-not-to-use guidance or pointer to get_candidate for fetching a single candidate by ID.

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