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

Beyond the annotations, it discloses cost-relevant behavior (reuse is cheaper), the need for a voice sample when cloning, and a usage-rights constraint that an agent should honor. It doesn't describe output format or latency, but it adds meaningful behavioral context and does not contradict any annotation.

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?

Two short sentences with the core mode decision front-loaded and a concise legal guardrail after it. There is no filler or repetition, and the content is easy for an agent to parse quickly.

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 4-parameter tool with no output schema, the description covers the primary purpose and mode selection well. But it doesn't state what happens if neither voiceId nor sampleUrl is provided, whether those two are mutually exclusive, or what the tool returns (e.g., an audio URL, job ID, or generated file). That leaves edge-case invocation and result handling partly to inference.

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 100% and every parameter already has a description, so the tool description dods little additional parameter-level work. Phrases like 'reuse a saved voice (cheaper)' and 'clone a NEW voice from a sample' essentially echo the voiceId and sampleUrl descriptions without adding new formats, constraints, or defaults.

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 the exact operation (clone or reuse a voice) and the resource (a voice used for speech), so an agent immediately knows this is a voice-cloning TTS tool. It distinguishes between NEW and saved voices, which also helps separate it from generic audio generation siblings like fattly_generate_audio. The annotation title 'Clone a voice' reinforces the purpose without conflicting.

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 a clear decision rule for the two modes: clone a NEW voice from a sample vs reuse a saved voice (cheaper), and it adds the important constraint to only use voices the user has rights to. However, it does not explicitly say when to prefer a different sibling tool such as fattly_generate_audio, so it stops short of a full when-not/alternatives statement.

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