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

Annotations only supply readOnlyHint=false; the description adds genuinely new behavior: a per-track cost of $0.05 at provider cost, and that the call returns an asset id rather than placing anything itself. Missing latency/async or failure behavior, which matters for a paid generative call.

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?

Two sentences with the cost flag front-loaded, then purpose, then return value and next step. Nothing is redundant with the schema and no sentence is wasted.

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 only three simple params, no output schema, and thin annotations, the description covers cost, output, and workflow handoff, which is what an agent needs to sequence the call. It could say more about duration limits or whether generation is synchronous, but the essentials are present.

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 mood, project_id and duration_seconds are already documented. The description only restates that the mood parameter drives generation; it adds no format, range, or enum guidance beyond the schema. Baseline 3 applies.

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?

Specific verb+resource: generates a background music track from a mood/style description, and it distinguishes itself from nearby siblings like studio.generate_voiceover or studio.add_sound by naming the output (audio asset) and the placement tool. An agent can tell exactly what it produces.

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?

States the follow-up action explicitly (place the returned asset id with add_audio_to_timeline), which is the key workflow context. It does not state when NOT to use it (e.g. vs. generate_voiceover or add_sound), so it stops short of full routing guidance.

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