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

Annotations only mark this as a non-readonly, open-world, non-idempotent write; the description goes well beyond them by disclosing pricing (2 credits per up-to-10s take, ~26 words), a 700-character input ceiling, an avatar tier that costs more and may be unavailable, and the asynchronous poll-list_creations pattern. It also flags the consent gate, which is the key safety behavior for this operation.

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 dense sentences, front-loaded with the capability, then cost, then the consent prerequisite and the follow-up action. No filler and nothing repeated from the schema verbatim.

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 6-parameter async generation tool with no output schema, it covers the essentials an agent needs — input limit, cost, consent, polling. It leaves open what the creation call immediately returns (an id/job handle) before polling, a minor gap given list_creations is named.

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 83%, so the baseline is already satisfied, and the description still adds real value: the 700-character cap on text and the 'any language' behavior are not in the schema, and the avatar model's higher cost/availity nuance sharpens the model enum. The voice parameter (only for the avatar model) is left unmentioned, which keeps this 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 concrete verb-plus-resource statement — a person's photo speaking the supplied text on camera — that is unmistakable and functionally distinct from siblings like create_video, copy_motion, or create_character. An agent can tell instantly which capability this tool provides.

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 gives clear operating context: consent=true is required for a real person, the avatar model costs more and is availability-dependent, and the agent should poll list_creations after submitting. It never explicitly routes the agent away from an alternative tool (e.g., create_video for non-talking footage), so it stops short of a 5.

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