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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description still adds real context: the auth prerequisite, the draft-only scope guard, the acknowledgement requirement, and a per-call cost note. It does not say what collateral state is removed (e.g. whether attachments/attached files go with the draft), which is the one behavior an agent might still want.

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?

Telegraphic and front-loaded: the hard prerequisite and the core action come before the exclusions. Slightly fragmented by the trailing Korean cost note, but no sentence is wasted.

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, 5-parameter mutation with no output schema, the description covers prerequisite auth, scope restriction, confirmation, the alternative path, and cost. Only the post-delete state (what is irrecoverably lost) is left implicit.

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 all five parameters are already documented, and the baseline is 3. The description adds one cross-parameter constraint — the login session must use the same account_link_id — but says nothing about programme_key, receipt_no, or business_management_no semantics.

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 (delete) and a precisely scoped resource (an unsubmitted work24 subsidy draft), and explicitly separates itself from the withdraw sibling for submitted applications. An agent can distinguish it from work24__subsidy__application__withdraw 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?

Gives an explicit precondition (prior work24__auth__npki_session__login with the same account_link_id), an explicit exclusion (submitted applications), and the named alternative to use in that case (withdraw). Both when-to-use and when-not-to-use are covered.

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