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

Annotations only say it is a non-destructive, non-idempotent write; the description goes well beyond by disclosing the async job contract (returns {id, status}, poll getApiJob), the credit hold/refund lifecycle with per-image scaling, the result payload shape (url plus applied rotation and elevation), and the request_id dedupe/tagging behavior with a pointer to listGenerations. The request_id reuse behavior sits in mild tension with idempotentHint=false, but only when the same request_id is supplied, so it is additive rather than contradictory.

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 purpose and sibling routing are front-loaded before operational details, and nearly every sentence carries information (types restriction, credits, polling, request_id). It is a dense single paragraph, though, and would read better split into purpose / params / job / billing lines.

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?

Despite having no output schema, the description specifies the result array contents and the intermediate job object, plus polling and billing semantics. For a nested-payload async generation tool, an agent has everything needed to call it, wait for completion, and account for cost.

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, yet the description still adds value: it enumerates the accepted camera_rotation azimuths (the schema declares no enums) and restates that camera_elevation may be omitted to preserve the current elevation, plus explains the request_id retrieval workflow. It does not add format or syntax details for image beyond what the schema already says.

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+resource+scope: re-render an existing sprite from a different camera viewpoint while preserving character and pose. It explicitly contrasts with generatePose (pose change), animateSprite and transferMotion (animation), so an agent can disambiguate it from the sibling set without opening schemas. It even restricts input types ('only works with sprite image types').

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?

States when to use it ('produce alternate view angles of a character') and names the concrete alternatives with the condition that selects each (generatePose for pose, animateSprite/transferMotion for animation). It also gives an exclusion ('not icons, screenshots, etc.'), leaving nothing to inference.

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