generate_song

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

No annotations are provided, so the description carries full burden. It discloses the async nature, expected duration (1-3 minutes), return type (job_id), and cost semantics ('Costs 10 tokens, billed only on success'). This is rich, non-obvious behavior.

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 earning its place: what it does, what to do next, and cost implications. Front-loaded with the critical async return behavior. No fluff or redundancy.

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?

The description fully covers the async workflow, necessary follow-up (wait_for_song), and billing. Given the rich parameter schema and no output schema, the description sufficiently explains return values and next steps. Sibling context is also handled by the explicit reference to wait_for_song.

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 description coverage is 100% and each parameter already has a clear description (e.g., custom mode, prompt semantics, idempotency_key). The tool description itself adds no parameter-level detail, which is appropriate given the schema already does the heavy lifting. Baseline 3 is warranted.

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 and resource: 'Start generating a song with Suno.' It clarifies the async behavior ('Returns immediately with a job_id') and explicitly states what the tool does NOT do ('does NOT return audio'), distinguishing it from wait_for_song.

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?

Explicit usage guidance: 'After calling this, call wait_for_song with the returned job_id to get the audio URL when ready.' This clearly tells the agent the next step and prevents misuse by calling this tool expecting audio.

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