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

The annotations only say readOnly/openWorld; the description adds genuinely valuable behavior: per-image pricing range ($0.006–$0.08), a mandatory $0.08 USDC x402 payment per call, the 1536 px per-side cap, and the store=true side effect that swaps inline data for a 7-day share link at an extra $0.001. The readOnlyHint=true sits uneasily with a tool that charges money and can persist a stored artifact, but that is an annotation weakness, not a description contradiction. What is still missing is what a non-store response actually looks like (URL, base64, mime type).

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 what the tool is, then models, then size limit, then pricing and the store option — a sensible information order with no filler sentences. There is mild redundancy between 'about $0.006 to $0.08' per image and '$0.08 USDC per call', which could momentarily confuse per-image versus per-call cost.

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 an 8-parameter paid generation tool with no output schema, the description covers the essentials an agent needs before calling: cost, payment rail, model selection, resolution cap, and the two output delivery modes (inline data vs 7-day link). Remaining gaps — response format specifics, latency, defaults for seed/steps — are modest given no output schema exists to carry them.

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 only 38%, so the description has to compensate and partially does: it explains the model options and their strengths, the 1536 px size limit (a bound absent from width/height in the schema), and the semantic of store. It says nothing about seed, steps (only that they affect price), or when negative_prompt applies (schema covers that as 'phoenix only'), leaving several parameters undocumented in both places.

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 ('Premium image generation') and names the exact models with their trade-offs (FLUX.2 dev for quality, klein 9B/4B for speed, Lucid Origin for photoreal/text, Phoenix). It is much more specific than the one-word title. It does not, however, contrast itself with the many sibling generation tools (image_generate, image_fast, images_generations), so the agent can't tell from the description alone why it should pick this one.

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 model-quality annotations ('highest quality' vs 'fast', 'photoreal, good text in images') give real in-tool guidance for choosing a model, and the pricing note implies cost-conscious selection. But there is no explicit when-to-use-this-tool-vs-alternatives guidance against siblings like image_fast or image_generate, and no statement of prerequisites (payment, x402) as a usage condition.

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