fish_generate_audio

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

With no annotations provided, the description carries the full disclosure burden. It states the return format ('JSON response containing task_id and audio data when complete') and gives an example. However, it does not disclose important behavioral nuances such as asynchronous behavior when callback_url is provided, or the fact that reference_id is typically required (the example includes it but no explicit statement). This is a moderate gap for a speech generation tool that may involve long-running tasks.

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 clear purpose statement, a 'Use this when' list, a return section, and an example. It is reasonably concise, though the two usage bullets are somewhat redundant ('convert text to speech' and 'AI-generated audio narration' are nearly identical). Overall, every section earns its place and the front-loaded purpose makes it easy to parse.

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?

This is a complex tool with 19 parameters and an output schema (indicated by 'Has output schema: true'). The description provides high-level use cases, a return format description, and an example, but it misses critical contextual guidance such as the asynchronous callback behavior, which parameters are required in practice, and how to choose a voice model. Given the tool's complexity and the lack of annotations, the description is not fully complete.

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 input schema covers all 19 parameters with descriptions, achieving 100% coverage. The description itself only references text and reference_id in the example, adding no additional semantic meaning beyond what the schema already provides. Therefore, a baseline score of 3 is appropriate.

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 opens with a specific verb+resource: 'Generate speech audio from text using Fish TTS.' This clearly distinguishes it from sibling tools like fish_get_task, fish_list_models, and fish_get_model, which are all retrieval-oriented. The purpose is unambiguous and differentiated.

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 a 'Use this when' section with two clear scenarios: converting text to speech and needing AI-generated audio narration. This gives clear context for when to use the tool. However, it does not explicitly mention alternative tools for related operations (e.g., fish_get_task for retrieving results), so it lacks exclusions or named alternatives.

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