Text to speech

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

Beyond the annotations (readOnlyHint=false, idempotentHint=false, openWorldHint=true, destructiveHint=false), the description adds genuinely useful behavior: per-character billing, the hard input-length ceiling, and the constraint that a cloned voice is bound to a specific route and model. It omits the return shape (inline audio bytes vs. a URL) and any failure modes, which matters since there is no output schema.

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?

Four short sentences with the core action and limit front-loaded, followed by voice handling and the billing note. Nothing is padding, and the sibling references are placed where an agent consuming the text will hit them before deciding how to call.

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 six-parameter synthesis call with no output schema and no nested objects, the description covers action, limit, voice resolution, route binding, and billing — enough to invoke it correctly. The remaining gaps are the return form of the audio and the semantics of speed and response_format.

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%: model, route, and voice are documented in-schema, while speed, response_format, and the input string carry no description. The description compensates well for voice (model-specificity, vv_ prefixes, route binding) and repeats the input length, but says nothing about speed units or what the six response_format values imply, so the gap is only partly closed.

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 first sentence gives a specific verb and resource ('Turn text ... into speech') plus the input constraint (≤ 4096 characters), which unambiguously separates it from the inverse sibling carpe_transcribe and from the non-synthesis sibling carpe_voice_clone.

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?

It gives concrete conditional guidance: omit voice to take the model default, use carpe_model_details to read a model's voices, and note that cloned voices only work on route "carpe" with the model they were cloned for. It does not explain when to choose route "router" versus "carpe", which is a meaningful decision left to the schema and the CARPE_DEFAULT_ROUTE default.

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