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

Beyond annotations, it discloses the asynchronous execution model, the returned generation_id, the polling requirement, and the per-song cost. This is exactly the behavioral context an agent needs and goes well beyond the readOnly/openWorld flags.

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?

Three short sentences, each carrying distinct value: purpose, cost, and async workflow. It is front-loaded and contains no filler.

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 tool with no output schema, the description adequately explains the invocation flow and how to obtain the result. It could be slightly more complete by noting what get_generation returns on failure or expected wait times, but the core flow is fully covered.

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%, with descriptions for prompt, lyrics, and is_instrumental. The tool description adds no parameter-level detail beyond restating that a prompt produces songs, so it relies on the schema.

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?

Description opens with 'Songs from a prompt,' immediately stating the resource (songs) and the input (prompt). The async detail with generation_id further distinguishes it from sibling generation tools by signaling it is not synchronous and pairs with get_generation.

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?

It provides clear usage context: input is a prompt and the result must be polled via get_generation. However, it does not explicitly say when to prefer this tool over siblings like ai_sound_effects or ai_voice_generator, nor does it state exclusions.

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