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 covered. The description adds genuinely useful behavior beyond that — reserved points are returned — but says nothing about what happens to the job payload, whether a completed job can still be cancelled, or what errors occur, and the doubled "무료. [무료]" is noise rather than information.

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 front-loaded opening sentence carries the effect and the refund, which is efficient. However, the trailing "무료. [무료]" duplicates the same fact twice in two formats, wasting the little space the description has and displacing more valuable state/precondition details.

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 one-parameter mutation with no output schema, the essential action and its point-refund effect are present, but a destructive operation warrants stating what is lost and under what conditions it succeeds. The cost marker is repeated while those prerequisites are omitted, so the description is only minimally complete.

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% and the single parameter job_id is documented in the schema ("내 문서 작업 ID"), so baseline 3 applies. The description adds no meaning about which job_id is acceptable — active only, owned by the caller, or reusable after cancellation.

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?

The description states a concrete verb and resource ("미완료 작업을 취소" — cancel an incomplete job) plus the side effect of refunding reserved points, which lets an agent distinguish it from creation/query siblings such as document_workflow_start or document_workflow_get. It never names the resource as a 'document workflow' job though, leaving the agent to infer the domain from the tool name alone.

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?

There is no guidance on when to cancel versus when to let a job finish, no mention of valid job states (e.g., only before document_finalize), and no reference to the sibling tts_jobs_cancel that covers the same operation for a different job type. The agent must infer the trigger condition entirely.

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