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

Strong on cost and lifecycle: credits are spent at prismposter.com parity, renders take one to a few minutes, results land in the user's library, and content involving minors or public figures is refused before charge. However, the description does not tie its behavior to the annotations and never states that the call is non-destructive or how retries are safe by default (the idempotency_key opt-in is documented only at the parameter level). With annotations already covering the safety profile, this adds cost and gate context but leaves the mutation/retry safety partly implicit.

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?

The first sentence is front-loaded and strong, but the paragraph sprawls into long run-on clauses with heavy parenthetical stacking (aspect ratio list, engine tradeoff, approval and refusal policy all in one block). Almost every clause earns its place, yet the same facts could be conveyed in half the space with clearer separation between capability, cost, and guardrails.

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 13-parameter generative tool with no output schema, the description covers what an agent needs to call it correctly: pricing, latency, polling, escalation to human approval, content refusals, and where output is stored. The remaining gap is the shape of the immediate return (job handle fields) and that failure of the description to reconcile with idempotentHint=false.

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 schema already explains every one of the 13 parameters, and the description correctly does not restate them. It does add value beyond the schema: @tag semantics for saved characters, end_image_url as a controlled transition, and platform-to-aspect-ratio mapping (9:16 for Reels/TikTok/Shorts) that an agent would otherwise have to infer.

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 plus scope: 'Make an AI video clip with sound from a prompt', and enumerates the controllable dimensions (camera moves, look, aspect ratio, engine). It is clearly distinguishable from create_image, change_video, extend_video and upscale_video, which are named later as follow-on tools rather than alternatives.

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: poll get_job after submitting, use quote_job to price first, continue with change_video/extend_video/upscale_video on an existing result, and start from a picture when a first frame is wanted. It also states the approval_required path and the refusal conditions, which are real when/when-not rules rather than generic context.

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