Generate image (Grok Imagine, GPT Image 2, Seedream V4, Wan, Imagen 4, Nano Banana, Ideogram V3, Z-Image Turbo)

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

Describes the job submission and polling process, credit costs, and the importance of aspectRatio. Annotations add minimal behavior info (readOnlyHint false, destructiveHint false), so the description carries the burden. It does not explicitly mention timeout behavior or error handling upon failure, which is a minor gap.

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?

Well-structured with a main paragraph followed by a bullet-point model selection guide. It is lengthy but appropriate given the tool's complexity (8 parameters, multiple models). Could be slightly more concise, but the organization makes it easy to scan.

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?

Covers usage, model selection, parameter details, and when to ask the user. No output schema exists, so the description should explain the return format, which it does succinctly ('returns the final image URLs'). Missing details on error handling or pagination, but sufficient for the tool's complexity.

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 100% (all 8 parameters documented). The description adds substantial value beyond the schema: detailed model selection guide, referenceImages usage, aspectRatio criticality, and numImages constraints. For example, the model parameter schema only says 'Defaults to...', while the description provides a comprehensive decision tree.

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 clearly states it generates images from text or text+reference images, specifies the default model and ability to get multiple outputs, and distinguishes from sibling tools like aetherwave_edit_image for I2I modifications. The verb 'Generates' is specific and the resource 'image' is clearly defined.

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?

Provides an extensive model selection guide with explicit when-to-use recommendations based on user intent (e.g., single high-quality output, photoreal, NSFW, cheapest). Also advises when to use aetherwave_edit_image for I2I changes and when to ask the user (contradictory prompts, expensive generations). Covers exclusion criteria and alternatives thoroughly.

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