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

Goes well past the annotations (destructive/openWorld): it discloses credit spend, refund on failure, asynchronous fire-and-return with a multi-minute completion time, the 10-minute dedup window, and the consent/child/public-figure policy. The requestId note explains the dedup contract that the idempotentHint=false annotation alone would not.

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 core action, then a numbered pre-call checklist and a files paragraph — good structure for a dense tool. It is long and somewhat run-on (the model list and the mode list in one sentence), but nearly every clause carries operational content.

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 28-parameter, nested, asynchronous, credit-spending tool with an output schema and full annotation coverage, the description covers the full lifecycle: preparation, invocation, polling, and delivery of the link. Nothing an agent needs to call it correctly and safely 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 adds a useful synthesis by grouping the two input paths (files attached in chat vs. public https *Url fields) and the prompt-reference convention. Slight deduction because "Clips must be links (MP4 or MOV)" sits at odds with the referenceClips file-object parameter in the schema, leaving an ambiguity the agent must resolve itself.

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 ("Make an AI video from the user's prompt") plus the supported input modes (text, start/end frame, references) and the model family. It is unambiguously distinct from sibling create_image and from get_model/get_creation, which it names as downstream steps.

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-flight sequence (pick model via get_model, quote the credit price, obtain consent) and an explicit post-call loop (call get_creation with wait true until ready, then give the link). It also states exactly when to reuse vs. generate anew via requestId within the 10-minute window.

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