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

Annotations already flag non-read-only, open-world, non-idempotent behavior; the description adds the return shape ({ style }), the endpoint, and the generation semantics (improve vs. invent vs. brief-from-lyrics). It does not disclose whether generation is synchronous or job-backed, which matters given the sibling acemusic_get_job, nor does it mention cost (left to the schema).

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?

Dense but front-loaded: capability, conditional branches, downstream use, and return value in three compact sentences with no filler. The long multi-clause opening sentence is slightly hard to parse on first read, but every clause carries 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?

Complete for a four-optional-parameter generation tool with no output schema: params are fully documented in the schema, the return value is stated, and the intended follow-up is named. The remaining gap is whether the call is synchronous or returns a pollable job, which is not stated despite the presence of acemusic_get_job.

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 100%, so a baseline of 3 already applies, and the description goes beyond it by explaining the semantic coupling between parameters: empty style triggers invention and lyrics only take effect with acemusic-v1. That conditional mapping is not expressed in the schema descriptions.

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 (improve a style description) plus the covered dimensions (genre, instruments, production) and the empty-input fallback. It also distinguishes the lyrics+acemusic-v1 branch as producing a production brief, so an agent can tell this apart from acemusic_write_lyrics or acemusic_create_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?

Gives explicit conditional usage: invent when style is empty, and write a production brief when model is acemusic-v1 and lyrics are supplied. It also names the downstream consumer (use the result as style in acemusic_create_song), but does not state when to avoid this tool or route elsewhere (e.g., for generating lyrics).

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