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

Annotations only declare it is not read-only, not destructive, and open-world; the description adds real economics (downloads are free, billing was counted once at conversion start) and a repeat-download safety protocol requiring user confirmation. It does not cover auth/permission requirements or whether output links expire, keeping it short of a 5.

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 short sentences, with the precondition and the artifact scope front-loaded and the repeat-safety caveat last. No filler or restatement of the title.

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?

An output schema exists, so return values need no explanation; the description covers the gating call, billing implications, and the repeat-confirmation workflow. The only material omission is the role of eventId, which neither schema nor description explains.

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 50%: kind and confirmRepeat are already documented in the schema, and the description merely reinforces confirmRepeat's rule. The undocumented eventId is never explained in the description, so it does not compensate for the coverage gap.

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+resource (download the completed voice conversion output) and names the artifacts available (cleaned vs standard). It implicitly separates itself from get_voice_conversion by tying invocation to that tool's completion status, though it never explicitly contrasts with the other download-ish siblings such as get_audio_download.

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 an explicit precondition ('Use after get_voice_conversion says the job is complete') and an explicit branch condition for the repeat case ('If the exact file was downloaded before, ask before retrying and then set confirmRepeat true'). The when-to-use and when-to-ask-first conditions are both spelled out.

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