Create an original music track from a text prompt. This consumes credits. Music renders synchronously: the result usually returns immediately with output_urls.
| Name | Required | Description | Default |
|---|---|---|---|
| style | No | ||
| lyrics | No | ||
| prompt | Yes | ||
| instrumental | No | ||
| duration_seconds | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the transparency burden. It does disclose important behaviors: the operation consumes credits, and it synchronously returns output_urls. However, it omits cost amounts, failure modes, rate limits, or what makes a prompt invalid, so the disclosure is thin rather than robust.
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 sentences, both load-bearing: the first defines the core action and the second covers side effects and timing. There is no filler and the most important constraints are front-loaded.
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 generation tool with five parameters, no annotations, and no output schema, this is minimally viable: the prompt is explained, credits are flagged, and the synchronous return behavior is stated. But optional parameter semantics, alternative tool routing, and cost nuances are missing, so it does not reach a higher level of completeness.
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 provides only types and constraints, not descriptions, so schema_description_coverage is essentially zero. The description adds meaning only for 'prompt' by saying the track is created 'from a text prompt,' but it entirely ignores the optional parameters: style, lyrics, instrumental, and duration_seconds. Since the schema carries no semantics, the description needed to compensate more and did not.
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 verb and resource: 'Create an original music track from a text prompt.' This is specific enough to distinguish from image, video, speech, and sound generation at a basic level. However, it does not explicitly call out any sibling tools or edge cases where it might be confused with 'generate_sound'.
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 explicit guidance about when to use this tool versus alternatives. Mentioning that 'This consumes credits' hints at a precondition, but it does not tell the agent when to choose this over other generators, when not to use it, or whether to check credits first.
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.
Every tool targets a distinct resource/action: generate_* tools are separated by media type, list_*/get_* tools cleanly separate overview from detail retrieval, and get_task vs wait_for_task are clearly one-shot status vs polling behavior. There is no real overlap or ambiguity among the 14 tools.
The tools follow a consistent verb_noun snake_case convention: generate_*, list_*, get_*, and wait_for_*. The generate_* group cleanly maps to each output modality, and the get/list distinction is applied predictably.
14 tools is well-scoped for a multimodal generation server. Each tool earns its place: generation for each media type, model listing/detail, voice enumeration, credit lookup, and task status handling. There is no obvious bloat or redundancy.
The surface covers the core workflow well: discover models/voices, create generations, retrieve outputs, and monitor credits. The main gap is the absence of an explicit task cancellation tool, but the persisted task statuses and wait_for_task workflow make this a minor gap rather than a blocking one.
