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

Annotations already declare the non-destructive, non-idempotent, open-world profile, and the description stays consistent with them. It adds real context beyond the annotations: the result is persisted to the media library as a hosted WAV, nothing is published or mutates video, and there is no separate credit allowance with normal API rate limits applying.

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?

Front-loads the core action, then adds scope and constraint sentences that each carry information. Minor redundancy between the title-like first line and the opening of the second sentence, but no filler overall.

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 four-parameter generative tool with no output schema and zero schema descriptions, the description omits the most decision-relevant facts: what the parameters mean, sensible value ranges, and any cost/latency expectations beyond rate limits. The safety and side-effect story is covered, but an agent still cannot call this confidently.

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 0% across four parameters (prompt, mood, bpm, duration) with no descriptions in the schema, so the description carries the full burden. It mentions no parameter at all — nothing about how prompt text should be phrased or how bpm/duration/mood are interpreted — leaving all four effectively undocumented.

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+resource ('Generate background music') and names the underlying service and the concrete artifact produced ('hosted WAV in your media library'). This clearly separates it from siblings like generateVideo, generateImage, and generateCaption.

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?

'Does not publish or change any video' implies a negative scope, so an agent knows this is a standalone asset-generation call rather than part of a publish flow. However, it never says when to reach for this versus generateVideo/mixVideoAudio, nor what prerequisites (e.g. brand context, model selection) are needed.

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