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

Goes well beyond the destructiveHint annotation: discloses auth prerequisite, the mutable-state constraint (작성중 only), the irreversibility gated by confirm, the required write mode, the success-verification rule (re-read attachment list), and per-call token cost. This is exactly the behavioral context a destructive write needs.

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-loads the auth requirement, then purpose, then constraints and verification. Dense but virtually every clause carries operational meaning; the internal endpoint fragment (deleteFileFormNxLn.do) is the only questionable inclusion.

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, no-output-schema write tool, the description covers prerequisites, state constraints, confirmation contract, success verification, and cost — everything an agent needs to invoke it safely.

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 100% and descriptions there already explain file_id (from draft_validate documents[].attached_files[].file_id), receipt_no, programme_key, and confirm. The description reinforces file_id provenance and confirm semantics but adds little parameter-level information beyond the schema.

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 resource (one file attached to a work24 subsidy draft), and even names the provenance of the identifier (file_id reported by draft_validate). An agent can distinguish this from application__delete or modify without opening the 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?

Explicit preconditions: must be preceded by auth__npki_session__login with same account_link_id, the draft must be in 작성중 state, and LIVE write mode plus confirm=true are required. It does not explicitly contrast with the sibling application__delete (whole-draft removal), so a small gap remains.

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