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

With readOnlyHint=false and openWorldHint=true already declared, the description usefully adds that the model is fixed and that a provider field must be omitted, preventing an invalid call. However, it says nothing about cost/latency, whether generation is asynchronous with a follow-up task lookup, or what the caller receives — meaningful gaps for a generative, non-deterministic operation.

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 sentences, no filler, and the model identity plus the hard request constraint are both front-loaded. Nothing would be lost or gained by rewording.

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 5-parameter generative tool with no output schema, the definition covers invocation well but leaves the return contract and any async/task-retrieval expectation unexplained. An agent knows how to call it but not what to expect back or how to obtain the resulting images.

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%, so prompt, imageUrls, outputNum, resolution and aspectRatio are already fully documented with constraints and examples. The description adds only the provider-omission rule, which is not itself a schema parameter, so it neither extends nor clarifies the declared fields.

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 ecommerce images') and pins the exact model ('Wan 2.7 image model'), which distinguishes it from the many sibling generation tools such as nexscope_wan_2_6_video_generation or the banana/gpt_image generators. It stops short of naming which sibling to prefer for non-ecommerce or non-Wan use cases.

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?

The only directive is a negative constraint ('provider must not be supplied'), which is a request rule, not a when-to-use rule. There is no statement about when to choose this model over the sibling image generators (banana, seedream, gpt_image) or when to prefer text-to-image versus reference-image mode.

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