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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is partly covered; the description adds non-obvious behavior beyond them — the no-time-limit rule, that it is refused once candidate activity begins, that history is preserved, and that the episode is excluded from admission reporting. These operational and reporting side effects are exactly the added value annotations cannot convey.

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 short sentences, each carrying distinct information (action, timing/refusal rule, side effects), with the core purpose front-loaded and no filler.

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 destructive, idempotent mutation with no output schema, the description covers preconditions, reversibility semantics, and reporting side effects well. The remaining gap is parameter-level detail, since none of the four fields are described in the schema.

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 0% with four parameters, so the description must carry the full burden. It only explains expected_admission_id ('its current admission ID', implying the concurrency check) and says nothing about application_id, request_id, or idempotency_key, leaving three of four parameters undocumented anywhere.

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 ('Correct one accidental candidate admission') and names the identifying key (the current admission ID). An agent can distinguish this corrective undo from the sibling yardstick_applications_admit_candidate without opening either schema.

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?

'No time limit; refused once candidate activity starts' gives a concrete precondition that determines when the call will succeed or fail. It is clear context, but it does not explicitly contrast the tool with alternatives such as admit_candidate or the transition/decide tools.

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