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

Annotations already declare non-readonly, open-world, non-idempotent behavior, and the description adds genuinely non-structural facts: priced by length, premium-mode requirement, a 15 s duration cap, and async polling via list_creations. It stops short of describing failure modes (e.g., what happens when consent is false or premium is off).

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?

One compact paragraph: what it does first, then cost/gating, then the consent prerequisite, then the polling instruction. Every clause carries operational information; nothing is padding.

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 4-parameter async generation tool with no output schema, the description covers purpose, cost, availability gate, required consent, duration limit, and how to retrieve results. An agent can call and follow up without further instructions.

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 the baseline is 3, but the description adds the 15 s video-length constraint that the schema does not encode, and reinforces that the image is a real person's photo when consent applies. Reasonable lift over the schema's own text.

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?

States a precise transformation: the person from a photo repeats the movement of a reference video, with concrete examples (dance, gesture, walk). This is clearly distinguishable from siblings like make_talking_photo or remake_from_reference without opening a 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?

'Only when premium video is switched on' is an explicit gating condition, and 'Needs consent=true for a real person' plus 'Poll list_creations' qualifies usage. It never names a competing sibling tool, so routing versus remake_from_reference is left implicit.

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