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

Annotations already mark destructiveHint=true, and the description adds meaningful context: it deletes only drafts, requires explicit caller acknowledgement, and requires a prior authenticated session. This goes beyond the annotation flags by clarifying what gets destroyed and under what conditions.

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 concise sentences with no wasted words. The prerequisite is front-loaded, followed by the action, the acknowledgement requirement, and the alternative. Every sentence earns its place.

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 operation with annotations covering the safety profile and full schema parameter coverage, the description provides the essential call context: prerequisite, target scope, confirmation, and fallback. No output schema exists, but a delete operation does not need return-value explanation.

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 the baseline is 3. The description does not add new parameter meaning beyond schema, but it correctly mentions account_link_id in the prerequisite and the confirmation requirement, reinforcing the confirm parameter's role.

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: 'Delete a work24 subsidy draft that has not been submitted.' It also distinguishes itself from the withdrawal sibling by explicitly saying submitted applications must be withdrawn instead. The Korean title reinforces the same scope.

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?

Explicitly names the prerequisite login call and the account_link_id requirement, states the condition under which this tool applies (unsubmitted drafts), and names the alternative path for submitted applications (withdraw). It also flags the confirmation requirement for destructive action.

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