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

The "Effects: interview outcome set; touch logged" line discloses a side effect (a history touch is written) that the annotations do not convey — readOnlyHint=false and destructiveHint=false only say it writes safely. What it omits is whether a closed round can be re-closed or corrected, which matters given idempotentHint=false.

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?

Front-loaded with the action, then semantics, then effects — a sensible order with little waste. The internal reference "(JH-12)" and the term "touch" are domain jargon that cost the reader a beat without adding operational value.

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 a non-idempotent mutation with no output schema, the essentials (required ids, outcome vocabulary, side effects) are present. Missing are preconditions and reversibility — whether the round must already be scheduled, and whether a wrong outcome can be corrected — which an agent needs before committing.

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 33% (only interview_id is documented), so the description has to compensate, and it largely does: it spells out the outcome vocabulary including "their no-show" for no_show_theirs, and frames notes as the place for interpretation rather than the verdict itself. The notes parameter's expected content is still only loosely defined.

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?

"Close a round" gives a specific verb and resource, and the following sentence narrows it to recording an interview outcome fact. It never names a sibling (e.g. hunt_add_interview or hunt_set_application_status), so the boundary between scheduling a round and closing one is left implicit.

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?

"Close the round when you know; the notes carry the interpretation" gives a timing cue but no explicit when-not or alternative tool. An agent can infer this is the terminal step of an interview, but there is no routing guidance against hunt_set_application_status or hunt_add_interview.

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