Create an audio clip (speech from text, or upload a recording)

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

With no annotations, the description carries the full burden and does well: it discloses the return value (clip id), the async completion pattern (ready when wait_for_job(model='audio-clip') reports done, usually seconds), the character cap, and how to handle long scripts. It omits cost/auth expectations, but for a creation tool this is unusually informative.

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?

Three sentences, front-loaded with purpose and mode selection, then return value and follow-up. The opening 'The soundtrack every video model takes as input' is slightly promotional but still functional as positioning; overall every sentence carries information.

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 and no annotations, yet the description covers the return type (clip id) and the readiness-check workflow via wait_for_job, plus the downstream consumption pattern. An agent has everything needed to invoke it and handle the result.

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% so baseline is 3, but the description adds real meaning beyond it: it makes explicit that text requires exactly one voice (voice_id or voice_user_id), that file_path is an alternative to text rather than a supplement, and that voice_user_id is specifically the cloned voice from list_voices with include_cloned. That mutual-exclusivity constraint is not obvious from the schema alone.

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?

States a concrete verb+resource ('create_audio_clip' producing speech from text or uploading a recording) and immediately frames its role as 'the soundtrack every video model takes as input.' An agent can distinguish it from sibling creation tools like create_craftstory2_video 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 lays out the two mutually exclusive modes — text (<=2000 chars) plus exactly one voice, OR file_path for an upload — which is exactly the decision an agent must make. It also routes onward to wait_for_job for completion and to create_craftstory2_video for multi-clip scripts, naming siblings by name.

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