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

Annotations only say destructive/not read-only; the description adds the critical facts an agent needs: the call spends user coins, unlimited-plan allowances do not apply, calls above a threshold return needs_confirmation, and refusal behavior for face-swap requests. It also flags that reference video length is priced.

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?

A single dense paragraph, front-loaded with the capability then the cost/confirmation workflow. Nearly every clause carries operational information, though the parenthetical about reference_videos_max is syntactically heavy and could be split for readability.

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 costly, destructive, multi-item generation tool this covers everything the agent needs: cost estimation, confirmation loop, idempotency via request_id (in schema), return values (task ids followed by get_tasks), and the refusal policy. An output schema exists, so return-format detail is correctly omitted.

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. The description adds a little beyond the schema — that reference videos are only usable for models whose reference mode lists reference_videos_max and that their length counts toward price — but the confirmation_token and max_total_coins mechanics are largely restated from the schema descriptions.

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?

Opens with a specific verb and resource: 'Generate 1–12 videos from text, a first frame, first and last frames, or reference images and videos.' The input modes named map to distinct parameters, and the tool is clearly separable from siblings like generate_image, extend_video, and edit_video.

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 explicit workflow instructions: call estimate_cost first, tell the user the price, handle needs_confirmation by asking the user and re-calling with the token, then follow task ids with get_tasks. It also names when-not-to-use (face swapping / real-person identity) and states such requests are refused.

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