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

Adds substantial context beyond the annotations: synchronous rather than a job, free/no credits, nothing persisted to generations, frames retained 7 days, multi-second latency, and the 204-no-body cancel behavior. The only gap is that it does not spell out what the `render_3d` payload contains field-by-field. Annotations (readOnlyHint=false, destructiveHint=false) are consistent with a non-persisting preview call, so no contradiction.

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 a one-line purpose, then behavior, then response shape, then the recommended workflow — a logical order with no filler. Some sentences are dense run-ons (the response-shape sentence in particular) and could be split for faster parsing, but every clause carries information an agent needs.

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, so the description carries the full burden of describing the response and does so: one preview per direction, ordering, `frame_urls` frame counts, and `render_3d` as a handoff to the render call. Combined with the free/non-persisted/latency notes and the cancel semantics, an agent has everything needed to call and interpret this tool.

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 already 100%, so the baseline is 3, but the description adds cross-referential meaning: the request body takes the same model/animation/camera/style fields as createDirectionalSprites, and `render_3d` from the response is fed back into that sibling unchanged. It also notes direction ordering and that each preview carries 4 frames for an animated model and 1 for a still.

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 ('preview') and resource ('directional sprites'), scopes it ('a few frames ... from each direction asked for'), and explicitly contrasts with the sibling createDirectionalSprites (preview-to-check vs full render). An agent can distinguish it from createDirectionalStills and createDirectionalSprites without opening any 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 explicit when-to-use guidance ('to check a style before rendering', 'Preview one or two directions while trying styles and render only once the look is right') and names the alternative render tool. It also states the serialization rule (one preview at a time, starting another cancels the older one), which prevents a common misuse.

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