Generate a new sound effect from an English text description (1-12 seconds). Rate-limited to 3/day per client. Output is CC0. Takes 10-60s.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | English description, e.g. 'heavy wooden door slam with echo' | |
| duration_s | No | Duration in seconds, 1-12 (default 4) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the behavioral disclosure burden and does so well by surfacing the 3/day rate limit, CC0 licensing, and 10-60s latency. It does not clarify whether the call is asynchronous or what the exact job/response semantics are, but it provides substantial operational context beyond the schema.
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 short sentences, each adding distinct value: the core purpose, the rate limit, and the output/licensing/latency constraints. There is no repetitive or filler content.
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 two-parameter generation tool, the description covers the key constraints: duration range, rate limit, license, and expected wait time. The only notable gap is that it does not describe what the API returns (e.g., a URL, binary audio, or job reference), which matters more because no output schema is provided.
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%, and both parameters are already documented in the input schema. The description adds little new parameter meaning beyond restating 'English text description' and the 1-12 second duration range already present in the schema, so it stays at the baseline.
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 states a specific action ('Generate'), a clear object ('a new sound effect'), and the input modality ('English text description'), making its purpose unmistakable. The word 'new' plus the sibling retrieval tools (get_job, get_sound, search_sounds) makes the distinction between creation and retrieval obvious.
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 phrasing 'Generate a new sound effect' clearly implies this tool is for creating sounds rather than retrieving existing ones, and the sibling names reinforce that retrieval is handled elsewhere. It does not explicitly say 'use get_sound or search_sounds for existing sounds,' so it stops short of a fully explicit when/when-not statement.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The tools are mostly distinct: generation, job status, metadata retrieval, and search each have clear purposes. get_job and get_sound could be confused at a glance, but their descriptions clarify the different identifier types (job_id vs slug).
All tool names follow a consistent verb_noun pattern: generate_sound, get_job, get_sound, search_sounds. This makes the API predictable and easy to navigate.
Four tools is well-scoped for a sound effect generation and search server. Each tool covers a necessary part of the workflow without redundancy or bloat.
The core lifecycle is covered: generate, check generation status, retrieve sound metadata, and search existing sounds. Minor gaps exist, such as no way to list all user-generated sounds or cancel a job, but these are not critical for the stated purpose.