generate_image

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

With no annotations provided, the description carries the full burden and meets it impressively. It discloses concrete side effects: files land in the generated-assets directory, a .json sidecar is written, and 'a taken name gets -2, -3, ...' (never overwrites). It reveals timing behavior ('high' can take over a minute), size-correctness caveats (rounded to multiples of 16, aspect-ratio bounds, result text reports actual size), and transparency/format coupling. It also states the return contract in detail, compensating for the missing output schema.

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?

The description is long but every sentence earns its place; there is no filler. It is front-loaded with purpose and usage routing, then uses labeled SHOUTED sections (SIZE, BACKGROUND, QUALITY, RETURNS) that make dense parameter logic scannable. The closing note about referencing the saved path tells the agent what to do with the result, closing an otherwise easy-to-miss loop.

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?

For a 7-parameter tool with no annotations and no output schema, the description is complete. It covers the operation, side effects (file writes, sidecar), parameter semantics with constraints, timing expectations, and a detailed return contract (absolute path, dimensions, model, quality, preview). Nothing an agent needs to invoke it correctly and interpret results is missing.

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?

Although schema coverage is 100%, the description adds substantial meaning beyond the schema: exact pixel dimensions for every size preset, rounding-to-16 rules, the 1:3–3:1 aspect-ratio bound, and the 3840-pixel maximum are absent from the schema. It adds the transparent-requires-png/webp constraint, explains quality trade-offs (low = fast/cheap for drafts, high = slow over a minute), and the filename never-overwrite behavior. This goes well beyond the baseline 3 justified by full schema coverage.

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 opens with a specific verb and resource: 'Generate one or more brand-new images from a text prompt... save them as files... return a small preview.' It explicitly contrasts with edit_image ('if you need the new image to match the look of images you already have'), so an agent can distinguish create-from-prompt from edit-from-reference without opening schemas. The phrase 'brand-new' signals no input image is required, which is the core differentiator.

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 explicit when/when-not rule: 'Use this when no existing image needs to guide the result. If you need the new image to match the look of images you already have... use edit_image instead and pass those files as references.' This names the sibling alternative and the exact condition that selects it — nothing is left to inference. The prompt-writing guidance (subject, style, composition, lighting, colour palette, text) is also actionable.

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