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

Beyond the annotations (which only flag non-readonly, open-world, non-idempotent, non-destructive), the description discloses credit cost (16 per 1,000 characters, rounded up), the async job model, and a detailed retry-safety contract for request_id including that replay returns the original job without recharging. That idempotency nuance is especially valuable given idempotentHint=false.

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?

Purpose and the sibling comparison are front-loaded, and the retry-safety block is clearly separated from the core description. It is long and repeats the voice list already present in the schema, but nearly every sentence carries operational information (pricing, polling, audio_ref chaining).

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?

Although there is no output schema, the description explains the return value (a job id to poll via get_run_status for the mp3 URL) and that the resulting URL can be chained into generate_video as an audio_ref. For a 5-parameter async generation tool, nothing an agent needs to call and follow up correctly is missing.

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 baseline is 3, but the description adds real meaning beyond it: the voice roster with gender/age characterizations, the cloned-voice Hebrew limitation, and the request_id reuse-vs-new-generation distinction. The tone enum and model parameter are left to the schema, and the voice list is partly duplicated from the schema description, keeping it from a 5.

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 a specific verb+resource ("Speak text in a named voice") and immediately enumerates the voice options. It explicitly distinguishes itself from the closest sibling by stating generate_video renders native speech when words are in the prompt, so an agent can route correctly without opening either schema.

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 states both when NOT to use it ("for a talking-head clip you usually do NOT need this") and when to use it instead ("voiceover over b-roll or a standalone audio file"), naming the alternative tool explicitly. Constraints like the Hebrew/cloned-voice rule further narrow correct usage.

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