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

Annotations declare a non-read-only, open-world, non-idempotent operation but say nothing about cost, latency, or lifecycle. The description adds the paid-plan requirement, the async contract (job_id returned immediately, 1–3 min render), and the rounding rule for unsupported durations — exactly the context annotations cannot carry.

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?

Front-loaded with the action, then the async contract, then the model/length table — no filler. The per-model length list is dense but every token carries decision-relevant information an agent needs before calling.

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 5-param generation tool with no output schema, the description covers the return value (job_id), the timing expectation, the required follow-up tool, and the model-specific constraints. Nothing an agent needs to invoke it 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 the baseline is 3; the description earns above that by documenting per-model allowed lengths (Seedance25 4/5/8/10/15/20/30s, Kling3 3/5/10/15s) and the rounding fallback, which the schema's min/max 3–30 cannot express. Minor gap: the schema mentions 768p for 'Hailuo', a provider not in the enum, and the description does not reconcile it.

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+resource: 'Start a text-to-video render', which cleanly separates it from generate_image, edit_image, and the other media siblings. The scope ('text-to-video', 'no faces') is stated up front rather than inferred.

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?

Explicitly routes the agent to check_video_status after submission and notes the paid-plan prerequisite, so the follow-up path is unambiguous. It does not explicitly say when to prefer generate_image or another model provider instead, which keeps it 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.