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

Annotations supply only readOnlyHint=false, so the description carries the load and does: $0.04 price, images stored in this workspace rather than provider links, refund semantics for OUTPUT_FLAGGED and RESULT_UNDELIVERED, and a named reason when download_url or preview is missing. That is exactly the behavioral context an agent needs before spending money.

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?

Purpose, cost and return shape are front-loaded before the error catalog, and the NEXT line closes it cleanly. The error list is long and reads as a run-on, but each entry is actionable rather than filler.

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?

There is no output schema, and the description compensates fully by describing the returned JSON keys, the preview block, the price field and next. Combined with error remediation and cost, an agent knows what it will get and what it will pay before calling.

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 75% and the schema already spells out request_ref idempotency and preview_format fallbacks in detail, so the description adds little there. The one gap — image_size's enum values — is not explained in the description either, only hinted at via "sized for editing."

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?

First sentence gives a specific verb (Generate), resource (an image), the model, and a distinguishing qualifier ("sized for editing") that separates it from the plain image.generate sibling. The downstream NEXT routing reinforces what kind of image this produces.

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?

Explicitly routes the agent forward ("pass images[0].asset_key as image_asset_key to image.inpaint, image.upscale or image.style_transfer") and gives retry guidance for transient errors. It never states the inverse condition — when to prefer image.generate over this tool — so the comparison with its closest sibling is left implicit.

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