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

Annotations already flag destructive=true and idempotent=false, but the description adds genuinely non-structured behavior: unpaid reservations are released, already-consumed paid processing is still settled, there is no additional charge, and a closing connection is not a cancellation. These billing/state semantics go well beyond the annotation layer.

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?

Four tight sentences: purpose first, then billing effect, then the connection caveat, then the charge note. Every sentence carries distinct information with no repetition.

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 single-parameter cancellation action with no output schema, the description supplies the job states affected, the billing outcome, and the footgun (connection close ≠ cancel). Nothing essential to calling it correctly 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?

Schema description coverage is 100% and the single job_id param is fully documented in the schema (32-char hex, '취소할 32자리 ID'). The description adds no extra syntax or format meaning beyond the schema, so the baseline 3 is correct.

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 (취소 요청/cancel) on a specific resource (waiting/processing TTS 작업), and scopes it to two job states. This cleanly separates it from siblings like tts_jobs_retry, tts_jobs_status, and tts_jobs_result without opening any 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 clear context for when it applies ('waiting 또는 processing TTS 작업') and adds the negative constraint that merely closing the connection does not cancel. It does not, however, name an alternative sibling for related needs (e.g. retry vs cancel), so it stops short of full when/where-not routing.

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