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

Annotations already communicate destructive intent, and the description adds behavioral and financial context beyond that: the initially charged amount is non-refundable and no additional charge is incurred. This helps the agent anticipate side effects. It stops short of saying whether cancellation is reversible or what final job state is returned, but those are secondary given destructiveHint=true.

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 definition is compact and front-loads the core cancellation semantics in one English sentence. The Korean sentences restate the same idea and add only [추가 과금 없음] as new detail, a minor redundancy, so it earns a 4 rather than a 5.

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-required-parameter, destructive operation the description includes the necessary usage condition (waiting/processing), the billing consequence, and an explicit no-extra-charge statement; the schema supplies the ID format. The absence of a return-value description is a small gap, but nothing essential for choosing or invoking the tool is missing.

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?

The only parameter, job_id, is fully described in the schema with a pattern, exact length, and a Korean description ('취소할 32자리 ID'). The tool description introduces no additional parameter semantics, so with 100% schema coverage the baseline of 3 is appropriate.

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 uses a specific verb ('Cancel') and a specific resource ('TTS job'), and narrows the operation to jobs in 'waiting or processing' states. It also states the billing consequence, which makes the tool's role unambiguous against siblings like tts_jobs_create, tts_jobs_status, and tts_jobs_result.

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?

It explicitly defines the only valid target states ('waiting or processing'), so an agent knows when cancellation is allowed and when it is not, such as for a completed job. It does not name alternative tools, but no sibling offers cancellation, so the when-to-use guidance is largely sufficient.

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