iterate_design

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

With only openWorldHint in annotations, the description carries most of the burden and does add real behavior: slow-model edits return 202 and are polled automatically, and multi-reference edits are constrained to specific models. It does not disclose cost, failure modes on rejected sources beyond Imagen, or what a polled result returns, so not fully transparent.

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 core sentence is front-loaded and dense with useful facts, but the trailing '[#63592e]' token is stray noise that earns no place, and cramming three model-support clauses into one paragraph slightly blurs the signal.

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 6 parameters, low schema coverage, and no output schema, the description covers async/polling behavior and model constraints but leaves `preserve`, `workspace`, and the shape of the returned variation unexplained. Adequate but with clear gaps for a nontrivial generation 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 only 33% across 6 parameters. The description meaningfully supplements `source` (which models support editing vs. multi-reference), but `preserve` (composition/subject/style) and `workspace` get no explanation anywhere, and `no_fallback` is documented only in the schema. Partial compensation for a low-coverage schema.

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: generate a variation of an existing design via img2img, with a concrete example. It is distinguishable from the sibling generate_image because it operates on an existing design, but it never names that sibling explicitly, so the differentiation is implied rather than stated.

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 useful model-selection context (almost every source supports editing; only Google Imagen 4 is rejected; multi-reference works on Seedream/Flux 2 Pro/Wan), which is guidance about the source parameter rather than about when to choose this tool over generate_image or design_apparel. No explicit when-not-to-use or alternative-tool routing.

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