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

Annotations already signal non-read-only and non-idempotent behavior. The description adds useful context about fixed vs. configurable durations per model. However, it does not disclose whether generation is asynchronous, what the return value is, or what happens if durationSeconds is passed to a fixed-duration model.

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 dense sentences with front-loaded purpose and no filler. Every clause adds useful information about invocation or model behavior.

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?

Covers core invocation and model-specific duration rules, which is sufficient for basic use. But it lacks default model behavior, folderReference semantics, and any indication of return format or async behavior, and there is no output schema to fill those gaps.

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%, so the description must compensate. It explains prompt, model, durationSeconds, and instrumental, and adds meaningful duration constraints per model that go beyond the raw schema. However, it omits folderReference entirely, leaving one parameter 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?

The description opens with 'AI music generation', a specific verb+resource phrase that clearly distinguishes this tool from sibling audio_tts and other creation tools. It also names the supported providers (Google Lyria, ElevenLabs) and key parameters, leaving no ambiguity about what the tool does.

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?

Provides concrete model-selection guidance by stating duration constraints: Lyria/Lyria-3 fixed 30s, Lyria-3-Pro 30–180s, ElevenLabs 10–300s. It does not explicitly say 'use this instead of audio_tts', but the 'music generation' framing makes the intended use case clear.

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