Generate a clip

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

Annotations only declare readOnlyHint=false/destructiveHint=false, and the description adds substantial context beyond that: per-second credit charging, failures charged nothing, idempotent replay of identical requests, and the generations_disabled/generations_marking_pending refusal states. The only gap is that it doesn't discuss async timing expectations beyond "poll", but pricing and failure semantics are unusually well disclosed for a write tool.

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 cost are front-loaded in the first sentence, then modes, workflow and reference formats follow in logical order. It is dense but nearly every clause carries operational meaning; the only slack is the restatement of the price range/quote guidance at the end.

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?

With 11 parameters, no output schema, and nested reference objects, the description supplies the workflow (quote, generate, poll), the success path ("generation.url is the clip"), the failure path (no charge) and the dedup rule. Missing only guidance on choosing model/resolution/camera, which an agent would otherwise have to infer from list_prices and list_generation_models.

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 description coverage is 0%, so the description carries the burden, and it explains the hardest parts: the three accepted reference shapes with rights_confirmed semantics, reusable_until for run_id references, and the 2% aspect-ratio tolerance for first_frame/last_frame. It also ties duration_s to billing and attempt to deduplication. It leaves model, resolution, aspect_ratio, camera and prompt uncharacterized, so it doesn't fully compensate.

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 specific verb and resource ("Generate one silent clip") plus the charging unit, and names the siblings it interacts with (quote_video, get_run, list_prices). It also enumerates its three modes, so an agent can distinguish it from generate_image or quote_video 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?

Gives an explicit pre-call step ("Call quote_video first and show the user the price"), a post-call step ("Poll the run with get_run"), and a fallback (list_prices names every price). It also states how to force a duplicate (pass attempt 2), which is exactly when-to-use-this-vs-what guidance.

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