generate_image

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

With no annotations, the description carries the full burden. It does disclose useful behavior: the operation queues (async), validation happens locally via the OpenAPI discriminator before any remote call, and the tool is disabled by default. It omits cost/paid-gating semantics implied by allow_paid and allow_unknown_cost, and never says what a successful call returns.

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 short sentences, front-loaded with the action, with no filler. The middle sentence leans slightly into implementation detail ('checked-in OpenAPI discriminator schema') but still conveys actionable validation behavior.

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?

This is an async queueing tool with a nested free-form parameter object, no annotations, and no output schema. The description never states what is returned (presumably a job id) nor that siblings such as get_image_generation or download_image must be used to retrieve the result, which is the most important missing context for an agent.

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 0%, so the description must compensate. It valuably explains that parameters is a free-form bag whose accepted keys are determined by model_id via the discriminator schema — something the bare schema (additionalProperties: {}) does not convey. It leaves allow_paid and allow_unknown_cost, arguably the most safety-relevant flags, entirely unexplained.

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 gives a specific verb and resource ('Queue an ElevenCreative image generation'), which is clearly distinct from siblings like generate_video, generate_music, or list_image_generations. It does not explicitly name an alternative or scope boundary, so a 4 rather than a 5.

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 'Disabled by default' note gives a genuine prerequisite an agent must handle before calling, which is more than nothing. However, there is no guidance on when to pick this over generate_video or how to choose a model_id, and no explicit statement of when-not-to-use.

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