change_voice

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

No annotations are supplied, so the description carries the entire behavioral burden and it discloses almost nothing: no file format/size constraints, no latency expectations, no upload behavior for the local path, and no mention of what happens on failure. Most importantly, the schema exposes allow_paid and allow_unknown_cost flags whose risk semantics (this operation can incur cost) are never explained despite being the highest-stakes aspect of the call.

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?

A single front-loaded sentence with no filler or repetition. It is efficient, though the brevity comes at the cost of the specification gaps noted elsewhere rather than from tight editing of sufficient content.

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 an 8-parameter audio-transformation tool with no annotations, no output schema, and no schema descriptions, one sentence is not enough to call it correctly. The agent lacks cost-safety guidance, default behavior for model_id and output_format, and any expectation about the returned artifact.

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 0% across 8 parameters, so the description must compensate and only loosely does: 'target voice' gestures at voice_id and 'local recording' at input_path, but filename, model_id, output_format, remove_background_noise, allow_paid, and allow_unknown_cost receive no meaning at all. Six undocumented parameters with non-obvious semantics (notably the two cost-safety flags) is a substantial 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 and resource ('transform a local recording into a target voice') and names the underlying operation ('speech-to-speech endpoint'), which distinguishes it from text-to-speech siblings like generate_speech and from isolate_voice. It stops short of explicitly differentiating itself from the neighboring voice tools, so an agent must infer the boundary.

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 use this instead of isolate_voice, generate_speech, or convert_audio, nor any stated prerequisites such as needing an existing source file on the local filesystem. 'Documented speech-to-speech endpoint' gestures at external documentation without providing the selection criteria an agent needs.

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