generate_image

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

With only openWorldHint=true in the annotations, the description carries the behavioral burden and does so well: it discloses the return value shape ('raw generated image'), the three-way rate-limit error taxonomy (model_rate_limited vs platform_rate_limited vs request_not_sent), and the fallback_trail substitution signal. This is exactly the kind of operational context an agent cannot get from the schema.

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?

Purpose is front-loaded, then the follow-up workflow rule, then error semantics — a sensible ordering with dense but non-padded prose. The stray trailing '[#e8fffe]' token is unexplained clutter that costs it a point.

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 7-parameter, multi-model generation tool with no output schema, the description adequately covers what comes back, what to do next, and the failure modes. It is silent on the cost/credit implication of a generation and on the workspace/style parameters, which prevents a 5.

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 57%, so the schema already documents size, source, no_fallback, and augment_prompt_for_transparency in detail, while style, prompt, and workspace are undocumented in both places. The description touches transparency indirectly (via process_transparency) and mentions fallback_trail, but adds no new parameter-level meaning beyond what structured fields provide, so the baseline 3 applies.

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 ('Generate a design image') and positions itself as the split primitive of design_apparel, which helps an agent separate it from the higher-level pipeline tool. It does not, however, distinguish itself from other image-producing siblings such as generate_listing_image or iterate_design, so the differentiation is real but partial.

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 one concrete sequencing rule: follow with process_transparency for apparel needing a transparent background. That is genuine conditional guidance, but there is no statement of when to prefer this over design_apparel (the pipeline it belongs to) or when not to use it at all, leaving the alternative-selection reasoning largely implied.

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