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

Beyond readOnlyHint and openWorldHint, the description discloses that no audio is produced, that only a language model reads the description, and that the output is JSON with events containing start, duration, and prompt. This gives the agent concrete behavioral expectations.

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 front-load the core action and the no-audio caveat, then add the sibling routing and output shape. Every sentence contributes without redundancy.

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 rich annotations and an output schema already present, the description supplies the missing context: when to use it, why it is cheap/safe, and what the result looks like. No essential call-time information is absent.

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%, and the description compensates for 'description' by calling it a long description and explaining how it is consumed. However, the 'seconds' parameter is never explained, even though it has a default and affects placement of events in time.

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 states a specific verb and resource: 'Turn a long description into sound events placed in time.' It also explicitly disambiguates from the sibling generate_sound_scene by saying 'Generates NO audio' and framing this as the planning step.

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 explicitly instructs to use this 'before generate_sound_scene when you want to see — or let the user correct — what is going to be made,' which identifies the alternative and the triggering condition. The cost note further clarifies when it is a safe and discriminating choice.

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