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

Annotations only cover the safety profile (readOnly, non-destructive, idempotent, open-world); the description goes well beyond by disclosing the async contract (jobId plus free pollUrl), cost (0.03 USDC per call), and latency (10000 ms p95). Output format (base64 JPEG) and provider/model are also given, which materially affects how an agent must handle the response.

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?

Front-loaded with the output contract and model, then usage, exclusions, price, and async timing — every sentence carries distinct operational information with no filler. Dense but not padded.

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?

Although an output schema exists (so return values needn't be spelled out), the description still explains the async handoff and pricing, and covers everything needed to invoke and follow up on the job. No material gap remains for a two-parameter generation tool.

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% and both parameters (prompt, steps) are already documented in the schema with ranges and defaults. The description adds no further meaning about parameter syntax or interaction, so the baseline 3 applies.

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+resource with full detail: generates a 1024x1024 JPEG from a text prompt via FLUX.1 schnell on Workers AI, returned as base64 JSON. It also implicitly separates itself from the sibling image-gen_v1_status by noting the call is asynchronous and returns a jobId to poll.

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?

Explicit 'Use when' clause (image generation/text-to-image for illustrations or mockups, and you can poll an async job) followed by an explicit 'Do not use when' clause listing four exclusion conditions (image edits, specific size, photos of real people, more than one image per call). This is exactly the when/when-not routing an agent needs.

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