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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, but the description adds substantial context beyond that: pagination via has_more, row fields, default sort semantics, filter behavior, and the deliberate absence of email/phone search. This gives the agent a complete behavioral picture.

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 dense but well organized: it front-loads the core list behavior, then return fields, then sort, then filters. Every sentence contributes useful information and there is no redundant restatement.

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?

Although an output schema exists, the description still explains the returned fields and pagination. For a 10-parameter filtered-list tool with no schema descriptions, it provides everything an agent needs to select and invoke the tool 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?

With 0% schema description coverage, the description compensates thoroughly by explaining sort meanings, status/stage filtering (including stage 'none'), shortlisted, min_score boundaries and drop behavior, date inclusivity/exclusivity, and name-search constraints. Even page and job_id are implicitly covered through pagination and 'The job's candidates'.

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 opening sentence clearly identifies the resource ('The job's candidates') and pagination behavior ('100 per page'), making it immediately distinguishable from get_candidate and other sibling tools. It also states exactly what each row contains and how the name field is exposed.

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 thoroughly explains when and how to use the filters, sort options, and pagination, including edge cases like rejected candidates and candidates not yet on the board. It does not explicitly name an alternative sibling tool such as get_candidate, but the usage context is clear enough for an agent.

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