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

Annotations already declare it is a non-read-only, non-idempotent, open-world, non-destructive write. The description goes well beyond that by disclosing the credit cost, the ~40-150 s generation time, the ~50 s wait-then-return-jobid async pattern, and the return format (clips with public m4a/wav links). This is substantial added behavioral context, though it doesn't cover failure/retry 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?

A single dense paragraph that front-loads what is generated, then the cost, then the async timing and result format, with no redundant or filler sentences. Every clause carries distinct information.

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 26-parameter, no-output-schema asynchronous tool, the description covers the aspects the structured data cannot: cost, latency, the wait-and-poll pattern with the named follow-up tool, and the shape of the returned result. Nothing an agent needs to invoke and follow up is missing.

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 baseline is 3 and per-parameter semantics are already handled. The description still adds useful cross-parameter meaning, explaining the lyrics-vs-model-written-lyrics-vs-instrumental interplay that the individual schema fields do not surface together.

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 (generate) and resource (song) via a named provider (Google Lyria / Flow Music), and enumerates the controllable dimensions (style, mood, genre, instruments, tempo, vocals) that define the input. It is readily distinguishable from siblings like flowmusic_cover_song and flowmusic_extend_song, which imply a source asset this tool does not require.

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?

Gives clear context for use: generation from a text description, with or without user lyrics, or instrumental, and explicitly notes it consumes the account's Flow Music credits. It also routes the agent to flowmusic_get_job after the wait window. It does not explicitly say when to prefer cover_song/extend_song/remix_lyrics instead, so the sibling-exclusion guidance is incomplete.

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