design_voice

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

With no annotations supplied, the description carries the full burden and does disclose non-obvious behavior: multiple sample audios are produced, they are written to local files and omitted from the tool response, and the call may consume credits. That is meaningful disclosure an agent could not get from structured fields. It stops short of naming where files land, how they are named, or what happens when credits are declined.

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, front-loaded with the action, followed by the response-shape caveat and the cost warning. Nothing is padded and the ordering matches what an agent needs before calling.

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 10-parameter mutation-adjacent tool with no annotations, no output schema, and zero schema coverage, the description leaves too much unknown: file naming and location, what an empty response actually looks like, and how the cost-consent flags gate the call. The return-omission note is valuable but the parameter surface is essentially undocumented.

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 10 parameters, so the description must compensate and it largely does not. It adds nothing about allow_paid, allow_unknown_cost, auto_generate_text, filename_prefix, guidance_scale, seed, loudness, or model_id. The single phrase 'may consume credits' faintly gestures at the two paid-consent flags but gives no guidance on how they interact.

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 names a specific verb and resource: 'Generate voice previews from a description.' That is concrete and unmistakable. It does not, however, differentiate itself from the nearby siblings create_voice_from_preview and get_voice_preview, which an agent could easily confuse with it in a list of 80+ tools.

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 statement of when to use this instead of create_voice_from_preview or clone_voice, no prerequisites, and no exclusions. The only implied workflow is generating samples that later feed a voice creation, and that has to be inferred rather than read.

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