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

Annotations already declare readOnlyHint=false and openWorldHint=true, so the baseline burden is lower. The description adds the genuinely useful constraint that provider is fixed and must be omitted, but says nothing about async task handling, latency, cost per image, or whether results must be fetched separately — gaps that matter for a paid generation call.

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, zero filler, purpose first and the hard invocation constraint second. Nothing is repeated and nothing is buried.

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?

The tool is a five-parameter generative call with no output schema, so the description must cover the full lifecycle and doesn't. It never explains what comes back (image URLs versus a task id) or how to retrieve results, which is significant given the sibling media_task_result tool that implies asynchronous completion.

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%, with the prompt, imageUrls, outputNum, resolution, and aspectRatio all documented in the schema itself, so baseline 3 applies. The description contributes only the negative constraint about provider, not any additional meaning about the declared parameters.

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 model to Nano Banana 2 Lite, so the agent knows exactly which generator this is. However, in a family of near-identical siblings (banana_2_1, banana_2, banana_pro, seedream_5_pro), it never says how this one differs in quality, cost, or capability.

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 one explicit rule — the model is fixed and provider must not be supplied — is a useful invocation constraint. But there is no guidance on when to choose this over the other banana/seedream/wan image tools, nor on when to pass imageUrls for image-to-image versus leaving it empty.

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