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

Annotations already declare non-destructive, idempotent, open-world behavior, and the description adds genuinely new context: nothing is rendered at this step, the variantId is only a draft, and credit consumption is conditional on start-frame generation. That is exactly the behavioral detail the annotations do not 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 core action, then cost, then workflow guidance, in roughly 50 words with no filler. Every clause adds decision-relevant information.

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 no output schema, the description does the work of naming the return shape ('Returns previewUrl and a variantId (a draft)') and explains cost and next-step workflow. The main residual gap is campaignId and the practical effect of idempotencyKey, which are left unaddressed in the description.

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 only 20%, so the description needs to carry more weight; it usefully clarifies that 'expression' means body language and that 'hook' is rendered as it will appear, and setting/expression enums are self-explanatory. However campaignId is never explained and hook's 90-char limit is left to the schema, so the gap is only partially closed.

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: 'Preview ONE variant's scene 1 before rendering anything,' and immediately clarifies the scope (character + setting + gesture, hook laid out as the video will show). An agent can distinguish this from autoshort_ugc_render_batch without opening either 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 workflow gate: 'Show the still to the user; render only after they approve,' which implies the alternative (batch/full render) and the condition that selects it. It also gives a cost rule ('1 credit only when a new start frame has to be generated; otherwise free'). It stops short of naming the sibling render tool outright, which keeps it from a 5.

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