preview_voice

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

With no annotations, the description must carry the full burden. It does disclose the key side effect of saving to disk and implies a short preview, but it omits details such as file overwrite behavior, network requirements, or any potential errors. It adds some context but not enough for a mutation-like operation without annotation support.

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 concise and front-loaded with the main purpose, followed by a clean list of arguments. Every sentence adds value, and the formatting is easily scannable. It loses a point for not being slightly more structured (e.g., using bold or separate lines for behavior vs args), but it is highly efficient.

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?

Given the tool has 4 parameters, no annotations, and an output schema, the description covers parameter semantics well but lacks usage context. It does not mention when to prefer preview_voice over synthesize_audio, nor does it detail any prerequisites beyond referencing list_voices. The output schema covers return values, so that gap is acceptable, but the missing differentiation and behavioral depth make it only partially complete.

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%, so the description must compensate, and it does. Each parameter is briefly explained: voice_id references list_voices, output_path specifies WAV writing, language_code is a locale, and text has a max length of 200 chars. This adds meaningful context beyond the bare schema, though it could be richer (e.g., exact formats for language_code).

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 clearly states the tool's function: 'Generate a short TTS preview and save it to disk.' It specifies a verb (Generate), resource (TTS preview), and an outcome (save to disk). However, it does not explicitly differentiate from the sibling 'synthesize_audio,' which likely performs full synthesis, leaving the distinction to inference.

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?

No guidance is provided on when to use this tool versus alternatives like synthesize_audio. The description does not mention any exclusions, prerequisites, or conditions for selection. An agent would have to infer that 'preview' implies a lighter operation, but this is not stated.

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