Generate an audio overview (podcast)

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

Annotations indicate `readOnlyHint: false` (state-changing) and `openWorldHint: true`. Description hints at async behavior via `artifact_wait` but does not explain that generation is asynchronous, might be long-running, or could incur costs. Lacks detail on what happens during generation.

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 concise sentences with critical information front-loaded. No redundant or extraneous content.

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?

Given 6 parameters (1 required) and no output schema, the description is too minimal. It fails to explain parameter usage (e.g., format options, `length`, `instructions`) or what the returned ID represents, forcing the agent to infer or experiment.

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 describes 6 parameters with 50% coverage. Description adds no parameter-specific meaning. Parameters like `instructions` and `sourceIds` are not elaborated, leaving the agent to guess their usage beyond schema hints.

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 clearly states the verb ('Kick off'), resource ('audio generation'), and return value ('task/artifact ID'). It explicitly pairs with `artifact_wait`, distinguishing it from sibling tools like `generate_video` or `generate_report`.

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 to 'pair with artifact_wait', providing usage context. However, it does not specify when not to use this tool, alternatives for different audio formats, or prerequisites like notebook existence.

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