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

Annotations only flag the tool as destructive/write. The description adds the semantics that matter: this is the terminal human decision, it never alters scores or evidence, outcomes are mutually exclusive per application, and mixed success is possible within a batch. That is exactly the context an agent cannot infer from annotations alone.

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?

Five tight sentences, front-loaded with what the tool does, then constraints and failure semantics. No filler or repetition of the parameter list.

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?

There is no output schema, and the description compensates by telling the agent to read every entry in 'results' for per-application outcomes. Combined with the reason/reopen prerequisites and the 'does not change scores' guarantee, an agent has everything needed 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 coverage is only 17%, so the description must carry weight and largely does: it explains candidateIds as applications capped at 100 per screening and states the conditional reasonId requirement that the schema does not encode. The optional 'note' parameter and the precise role of batchId are left unmentioned, a small remaining gap.

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 a specific verb and resource ('Record ... hiring outcome') plus scope ('up to 100 applications in one screening') and the allowed outcome values. It explicitly separates itself from screening gate, stage, archiving and reviewer verdicts, which routes the agent away from set_candidate_stage, reject_candidate and set_candidate_review without opening their schemas.

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?

Gives explicit preconditions: rejected/withdrawn require a reasonId from list_hiring_outcome_reasons, and an application with a different existing outcome must be reopened first (pointing to reopen_hiring_outcome). It also sets expectations for partial batch results ('each application succeeds or fails on its own').

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