convert_voice

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

With no annotations, the description carries the full burden. It discloses core behavior (voice swap preserving timing), format downgrade behavior ('wav auto-downgrades to mp3 on sub-Pro tiers'), and noise removal as a pre-processing step. However, it omits potentially important side effects such as whether the original audio file is modified, network/credit consumption, or authentication requirements.

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 well-structured with a brief summary, a use-case sentence, an Args block, and a Returns block. Every sentence adds value; there is no redundancy or filler. The front-loaded summary immediately conveys what the tool does.

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 tool with five parameters and no output schema, the description is remarkably complete. It includes a return format, parameter details, and specific format/behavior nuances. Minor gaps include explicit error scenarios and prerequisites (e.g., account tier or parent workspace), but overall it is self-contained enough for an agent to use correctly.

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 0%, so the description must compensate, and it does. Each parameter gets a functional explanation beyond the schema: audio is 'Local path to the source audio', voice is 'a saved name or an ElevenLabs voice id', format includes allowed values and downgrade caveat, and seed is 'Optional determinism hint.' All five parameters are addressed, though 'seed' could be more precise about its effect.

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 action ('Re-voice a recorded performance onto another voice') and the resource (ElevenLabs speech-to-speech). It explicitly distinguishes this from sibling tools by emphasizing that it 'keeps the delivery/timing of the input recording but swaps the voice,' positioning it for dubbing, ADR, and character voice conversion.

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?

The description gives clear use-case context: 'for dubbing, ADR, or turning your own take into a character's voice.' It does not explicitly name alternatives or state when not to use, but the distinction from text-to-speech tools (like generate_speech) is strongly implied through the focus on existing recordings.

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