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

Annotations already cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true, idempotentHint=false), so the description's job is to add context it does and does well: credit cost scales with count (4/6/8 credits) and the call is asynchronous, requiring polling via list_creations. It does not say what a failed/partial generation looks like or whether credits are refunded.

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?

Two dense sentences: the capability and its angle vocabulary first, then the pricing mapping, then the polling instruction. Every clause is actionable and nothing is padded.

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 3-parameter, no-output-schema, credit-consuming generation tool it covers input pointer, cost, and the required polling step. It omits how to locate the resulting set in list_creations output and what leads to a partial or failed run, which matters for an asynchronous paid operation.

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 67% and count has only an enum with no description; the description supplies the missing meaning by mapping each count to its credit price, which the schema does not convey. The angle vocabulary (three-quarter, side, top, macro, low, front, wide, detail) also enriches the count parameter since those angles are what the returned set contains.

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+resource: producing new camera angles (three-quarter, side, top, macro, etc.) of the same shoot from a single photo. This clearly separates it from generic siblings like create_image or generate_photos, though it never names an alternative explicitly.

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?

"Poll list_creations" gives the required follow-up step after invocation, which is genuinely useful workflow guidance. However, there is no statement of when to prefer this over remake_from_reference, create_image, or generate_photos, and no prerequisites are given beyond the image link hint in the schema.

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