Generate image

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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false and destructiveHint=false. The description adds real value beyond that: it discloses the return shape (image content plus metadata) and the optional side effect of writing a new local file, which the annotations alone don't convey. It stops short of mentioning cost, rate limits, or provider auth requirements, which matters for a non-idempotent, open-world 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?

Three sentences, front-loaded with the core verb and resource, then the provider scope, then the return behavior and the disambiguation. Almost every clause earns its place, with only minor redundancy between 'Returns image content' and the later clarification.

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?

With no output schema, the description correctly fills the gap by describing the return (image content and metadata) and the optional file write. All parameters are schema-documented and safety traits are annotated. The remaining gap is operational context, such as which provider settings are read from configuration and whether generation costs or rate limits apply.

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%, so all four parameters (prompt, size, quality, output_path) are documented in the schema, including provider-specific caveats like quality being unsupported by Ark. The description only echoes the optional file-saving behavior for output_path and adds no syntax, defaults, or provider-selection logic beyond the schema. Baseline 3 is appropriate when the schema does the heavy lifting.

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 (Generate) and resource (one image from a text prompt), names the supported providers, and explicitly separates itself from the analyze_image sibling with 'This is image creation, not image analysis.' An agent can distinguish it from siblings without reading any schema.

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?

Clearly establishes the context: image generation from prompts, provider-agnostic, and independent of native vision capability, with an explicit statement that it is not image analysis. It does not explicitly say when NOT to use it (e.g., editing an existing image) or name analyze_image directly as the alternative, which leaves a small inference gap.

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