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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description adds genuine beyond-schema context: a fixed page size of 25, the presence of an AI match score only when ranking exists, and a data-provenance caveat that names and emails are applicant-written (i.e., untrusted input). It does not describe pagination termination or how ordering interacts with the AI match when unranked.

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?

Three compact sentences, with what it returns and how it pages front-loaded ahead of the sorting default and the provenance note. Nothing is padded, though the final sentence about applicant-written names is terse enough that its implication is left for the reader to infer.

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 carries the return-shape burden and does so adequately: it names the AI match field and its 0–1 range, mentions name/email presence, and specifies page size and default ordering. Combined with the annotations and the 80%-covered schema, an agent has enough to call it correctly.

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 description coverage is 80%, so the baseline is 3. The description confirms the default best-match sort and the one-stage scoping that maps to stageId, and the 25-per-page note ties to the cursor parameter, but it adds no format or semantics beyond what the schema already documents.

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?

"Lists a job's applications in one stage, 25 at a time" gives a specific verb for a specific resource plus scope (single stage, paginated). It implicitly separates itself from get_application (singular retrieval) by describing a paginated listing, and from list_jobs by naming applications as the resource, though it never names a sibling explicitly.

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?

Usage is implied rather than stated: the description tells you it browses one stage of a job's applications and defaults to best-match ordering, which hints at the primary use case. It offers no explicit when-to-use versus get_application or list_jobs guidance, and no exclusions or prerequisites beyond the stage scoping.

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