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

With no annotations, the description carries the full burden, and it discloses the key traits: asynchronous start returning immediately with status 'queued', the need to poll, that the operation 'Spends credits', and that the API key is required to retrieve video_url. Missing are cost magnitude, expected generation time, and what happens to credits on failure — meaningful gaps for an expensive async mutation, but the core behavioral contract is present.

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?

Three short sentences, all front-loaded with the action first and the follow-up workflow second. Every clause carries information: what it does, what it returns, how to poll, how to surface the result, and the credit cost.

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?

There is no output schema and no annotations, so the description must explain the return contract itself — which it does by stating the immediate 'queued' status, the polling loop, and the two ways to get a usable link. For an async, credit-spending creation tool, an agent has everything needed to call it correctly.

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 100%, so every parameter (url, prompt, images, aspect, seconds, voice, purpose, model) is already documented in the schema, including enums and defaults. The description only reinforces that url and prompt are alternative or combinable inputs. Baseline 3 applies since the schema does the heavy lifting.

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 ('Start a motion video') and names the two inputs that can seed it ('from a public product URL or a prompt'). It also differentiates itself from siblings by naming get_video and share_video as the follow-on tools, so an agent can place it in the pipeline 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 usage chain: start, poll get_video until 'ready', then surface video_url or call share_video. That is clear contextual guidance for how and when to invoke it and what to do next. It stops short of explicit exclusions — nothing says when to prefer revise_video over creating a new video — so it is not a full when/when-not statement.

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