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

The description goes beyond the annotations by clearly stating that the server original is consumed on the first call and cannot be re-executed, matching destructiveHint=true. It also adds the context that there is no additional charge ([추가 과금 없음]), which is useful operational information an agent would need before invoking a destructive operation.

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 description is compact and front-loaded, with the core action in the first sentence and the critical consumption warning immediately after. The bilingual repetition adds some redundancy but remains efficient and clear.

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, destructive download tool with no output schema, the description covers everything needed: what to download, the format, the completion precondition, the one-time consumption behavior, and cost implications. It is fully self-sufficient for correct invocation.

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%: the job_id parameter already has a description ('completed 상태인 32자리 ID'). The tool description does not add new meaning to the parameter beyond what the schema provides, so the baseline of 3 applies.

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 specific verb ('Download'), a specific resource ('completed MP3 result'), and the exact output encoding ('as base64'). It clearly distinguishes this from sibling tools like tts_jobs_status (status check) or tts_jobs_subtitles (subtitle download) by specifying the result file itself.

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?

The description provides clear usage context: the job must be 'completed' and the result can only be downloaded 'once'. It implies this tool is for the final retrieval step after creation and status checks, though it does not explicitly name alternative tools or state when not to use it.

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