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

Annotations declare a non-destructive, non-idempotent, open-world write; the description layers on genuinely useful behavior the annotations cannot convey: no audio is rendered, credit consumption is small, and latency is ~30 s. The cost and timing disclosures are the main value add.

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?

Five short sentences, densely front-loaded: what it produces, what it does not do, cost, latency, and next step. The trailing endpoint ('POST /music/lyrics') is minor but harmless.

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 3-param tool with no output schema, the description covers what comes back (lyrics, title, sound prompt) and where to send it next, plus cost and latency. A brief note on output shape/formatting of the returned lyrics would close the remaining gap.

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%, so the schema already documents prompt, structure and email; baseline 3 applies. The description's [Verse]/[Chorus] formatting hints lightly reinforce the 'structure' parameter but add no semantics beyond the schema.

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: writes lyrics (with [Verse]/[Chorus] markup), a title and a sound prompt. The scope negation 'without making audio' cleanly distinguishes it from flowmusic_create_song, which it explicitly names.

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?

Tells the agent when to use it (concept-to-lyrics without audio) and gives the downstream step: 'Pass them to flowmusic_create_song.' It does not, however, address the nearby alternative flowmusic_remix_lyrics or say when to pick that instead.

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