fish_generate_audio

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

No annotations are provided, so the description carries the burden. It mentions the return format (JSON with task_id and audio data) and shows an example, which is helpful. However, it doesn't disclose potential side effects (e.g., cost, rate limits, async behavior details) or clarify that the tool may return immediately with a task_id when async is used. The description adds some value but could be more transparent about asynchronous behavior and error cases.

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 concise and well-structured with a clear purpose, usage conditions, return format, and example. It's front-loaded with the main purpose and uses bullet points for readability. The example is useful but could be slightly trimmed. Overall, it's efficient and earns its place.

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?

Given the tool's complexity (20 parameters, async options, multiple models), the description is somewhat minimal. It doesn't explain the async behavior, callback_url usage, or how to choose between models. The output schema exists, so return values are covered, but the description could provide more context on when to use async vs sync, and how to handle the task_id for polling. It's adequate but not comprehensive for such a complex tool.

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?

The schema description coverage is 100%, so the schema already documents all 20 parameters. The description adds minimal extra meaning beyond the schema, only mentioning the example reference_id and the text parameter. It doesn't explain relationships between parameters (e.g., async vs callback_url) or provide guidance on which parameters are commonly used together. Baseline 3 is appropriate since the schema does the heavy lifting.

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 tool's purpose: 'Generate speech audio from text using Fish TTS.' It specifies the verb (generate), resource (speech audio), and the technology (Fish TTS). It also distinguishes from siblings by focusing on audio generation, while siblings like fish_get_task or fish_list_models handle retrieval and listing.

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 provides explicit 'Use this when' conditions: converting text to speech and needing AI-generated audio narration. It doesn't explicitly mention when not to use it or alternatives, but the sibling tools (e.g., fish_get_task for retrieval) imply a clear separation. The guidance is clear but lacks explicit exclusions.

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