Write a song

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

Annotations supply only openWorldHint=true, so the description carries the behavioral load — and it delivers: credit cost ('60 credits a run'), auth requirement ('needs TANVO_API_KEY'), and what a run actually produces (two takes, each an MP3 with cover art, title, and sung lyrics). It doesn't cover async retrieval when wait=false, but cost and auth disclosure is substantive context beyond the annotations.

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 sentences, front-loaded with what the tool produces before the mode table and the cost/auth constraints. Every clause carries information — output format, mode semantics, pricing, credential requirement — with no filler or restatement of the name.

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?

With no output schema, the description correctly compensates by describing the return (two takes, MP3, cover art, title, lyrics) and adds cost/auth/mode detail. The one gap is that it never mentions the async path — when wait=false the agent presumably needs get_generation to fetch results — which matters for correct invocation.

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 71%, and the description adds real meaning on the highest-stakes parameter by explaining how prompt and mode interact, which the enum alone cannot convey — the same string means a one-line brief in Describe but full tagged lyrics in Lyrics. The remaining params (wait, save_to, title, vocal) are left to the schema, which is acceptable at this coverage level.

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?

States a specific verb and resource ('Makes two takes of a song on Suno V6') plus the concrete output (two MP3s with cover art, title, and lyrics as sung). This clearly distinguishes it from siblings generate_image, generate_video, and generate_from_app without needing to name them.

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 mode breakdown ('Describe' = one-sentence prompt, lyrics written for you; 'Lyrics' = your lyrics with [Verse]/[Chorus]/[Bridge] tags; 'Instrumental' = prompt describes the sound) tells an agent exactly how to choose the mode and what to put in prompt for each. There are no explicit exclusions or routing rules versus sibling generation tools, so it stops short of a 5.

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