sound_generation

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

Annotations cover the operation profile (readOnly=false, idempotent=false, openWorld=true, destructive=false), and the description usefully adds context the annotations do not: that the call consumes ElevenLabs credits (a cost/side-effect disclosure) and that the return payload is audio/mpeg bytes. It stops short of permission/tier requirements or failure behavior, but it clearly pulls its weight beyond the structured fields.

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, front-loaded sentences with no filler. The cost warning leads, followed by the return-handling note, which is a sensible ordering for an agent. It is terse almost to a fault, but nothing in it is wasted.

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 7-parameter, non-idempotent, credit-spending generation tool with no output schema, the description covers the biggest agent concern (output delivery and cost) but omits the actual generative purpose and leaves duration_seconds and prompt_influence entirely undocumented anywhere. It is adequate but leaves real gaps.

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 57%, and the description only echoes the output_path behavior ("pass output_path to save them") that the schema's own output_path description already states in more detail (relative path resolution against ELEVENLABS_OUTPUT_DIR, inline base64 fallback). It adds no meaning for duration_seconds, prompt_influence, or model_id, which carry no schema descriptions at all.

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?

"Sound Generation" essentially restates the tool name/title rather than stating a verb+resource with scope; the actual function (converting a text prompt into a sound effect) is only discoverable from the schema's `text` description. It also fails to distinguish itself from near-neighbors like text_to_speech_full, create_video_generation, or video_to_music, which occupy adjacent audio-generation space.

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?

There is no when-to-use, when-not-to-use, or alternative-tool guidance. The only usage-relevant content is the implicit cost warning ("Spends ElevenLabs credits") and the output_path hint, neither of which helps an agent decide between this and the other audio-generation siblings.

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