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

Annotations declare readOnlyHint=false and openWorldHint=true, so the description should add operational context such as cost, latency, sync vs. async behavior, or how results are retrieved. It adds only the useful constraint that the provider is fixed and must be omitted — nothing about whether the call returns images directly or a task ID to poll (a sibling media_task_result tool hints at async).

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 short sentences with zero filler; the core action is front-loaded and the request constraint follows immediately. Nothing could be removed without losing information.

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?

No output schema exists, so the description is the only place an agent could learn what a successful call returns (image URLs, task handle, expiry). It says nothing about the response, and with ten-plus competing image models it gives no basis for selection, leaving significant gaps for a 5-parameter 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 description coverage is 100%, including formats, ranges, and enum lists, so the schema carries the parameter burden and baseline is 3. The description adds one genuine beyond-schema fact — that a provider parameter must not be sent despite additionalProperties=true — which slightly exceeds the baseline but does not cover prompt/imageUrls semantics.

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?

The description names a specific verb and resource ('Generate ecommerce images') and pins it to a named model, so the agent knows exactly what it produces. It never distinguishes this model from the many other image-generation siblings (banana_pro_image_generation, gpt_image_2_generation, wan_2_7_image_generation), so an agent cannot tell why this one over another.

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?

'Generate ecommerce images' weakly implies a domain of use, but there is no statement of when to pick this versus the other image models, no prerequisites, and no exclusions. The only guidance offered ('provider must not be supplied') is a request-shape rule, not usage guidance.

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