createClonedVoice

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

With annotations covering only the safety triad (not read-only, not destructive, closed-world), the description adds substantial behavior beyond them: asynchronous creation with 202/processing, the 429 refusal on limits, the 5/hour, 20/day, 200-stored quotas, and the fact that the consent attestation is recorded against the clone. This is exactly the operational context annotations cannot carry.

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?

Paragraphs are short, front-loaded, and each carries actionable content (formats, async flow, consent, limits). Slight redundancy with the schema on the clip constraints and the consent requirement keeps it from a 5, but nothing is padded.

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?

No output schema exists, and the description compensates by describing the return contract (202 with status: processing), the status states, and how the resulting voice_id is consumed. For a nested-body, async mutation tool, an agent has everything needed to call it 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 description coverage is 100%, so the clip size range (1 KB–25 MB), accepted formats (MP3/WAV/WebM), and consent=true are all already documented in the schema. The description restates these rather than adding syntax or format detail beyond them, so the baseline 3 applies.

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?

Opens with a specific verb+resource ('Clone a voice from an audio sample') and immediately names the input medium and accepted formats. An agent can distinguish it from siblings like getClonedVoice, listClonedVoices, and regenerateClonedVoiceSample without opening the schema.

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?

Explicitly describes the full workflow: synchronous 202 return, polling GET /voices/{voice_id} until status is ready or failed, then using voice_id with voice.provider cartesia. It also states the consent precondition and the per-user rate limits, so the agent knows both when to call and when a retry will be refused with 429.

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