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

Annotations already flag destructiveHint=true, but the description adds real operational context: the auth-session prerequisite bound to the same account_link_id, the mandatory explicit acknowledgement, and a per-call token cost. It stops short of saying what state the application lands in after withdrawal or whether the receipt number stays valid.

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 hard prerequisite is front-loaded in the first sentence, and the token-cost note is short and last. "Requires explicit caller acknowledgement" partly duplicates the confirm parameter's schema description and the destructive annotation, so that sentence earns less than the others.

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 mutation with no output schema, the description covers auth, confirmation, reversibility framing, and cost. It leaves unclear what the response reports and what the caller should do if the withdrawal is rejected, which matters for an irreversible operation.

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 100%, so every parameter is already documented, and the baseline of 3 applies. The only added semantic is tying account_link_id to the prior login session, which is useful but marginal against the schema's existing per-field detail including the receipt_no provenance.

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 ("Withdraw a submitted work24 subsidy application") and frames it as "the undo for submit," which separates it from the submit sibling. It does not distinguish itself from the nearby work24__subsidy__application__delete sibling, so an agent comparing the two gets no help choosing.

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?

"REQUIRES prior work24__auth__npki_session__login call with same account_link_id" gives a concrete precondition, and "undo for submit" implies the triggering situation. No exclusions are stated, e.g. whether this works on a draft or how it differs from delete, so the agent must infer the boundary cases.

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