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

Annotations already declare non-read-only, non-idempotent, non-destructive behavior, but the description adds crucial context beyond them: each version costs the original image's credits (usually 1), new versions are placed next to the old ones, and it returns new generation ids. It does not cover failure modes or concurrency, but the cost and placement details are the important additions here.

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?

Four tight sentences, front-loaded with the core action, then cost, exclusions, and return flow. No filler or repetition.

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 credit-consuming generation tool with no output schema, the description covers what it does, what it costs, what it returns, and what to call next. It is complete enough to invoke correctly, with minor room for error-handling detail.

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 both parameters are documented structurally. The description still adds meaning by clarifying that versions are 1–5 new versions made at once and that each one is billed at the original image's credit cost, which the schema does not state.

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: makes one image of a set again with the same prompt as 1–5 new versions. It explicitly distinguishes itself from edit_image (not for the main image on white) and names the sibling to use for that case, so an agent can tell the tools apart 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 explicit when-to-use (to pick the best version via pick_image_version), when-not-to-use (not for the main image on white; use edit_image), and the expected follow-up call (get_image_set). Nothing is left to inference.

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