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

Beyond the single readOnlyHint=false annotation, the description discloses price ($0.07), that outputs live in this workspace rather than provider links, preview behavior, and a full catalogue of refusal codes with their remedies — including which ones are refunded and which are free to retry. This is exactly the context annotations cannot carry.

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, mask requirement, and return shape are front-loaded, and the long error enumeration earns its length by mapping each code to an action. The result is one very dense paragraph, though, and a short structured error list would scan faster.

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?

With no output schema, the description still specifies the exact return envelope ({images:[...], price, next}), explains download_url_unavailable and preview behavior, and describes all failure modes. An agent has everything needed to call it and handle the result.

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%, so every parameter is already documented. The description's contribution ("Pass a mask covering the sky (white = sky)") largely duplicates the mask_url and mask_asset_key descriptions rather than adding new semantics; the baseline 3 applies when the schema does the heavy lifting.

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 ("Replace a photo's sky") plus the model used (FLUX Fill) and the core requirement (a mask with white = sky), so an agent knows exactly what it produces. It does not explicitly differentiate from close siblings like image.inpaint or image.replace_background, which an agent would have to disambiguate on its own.

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?

It clearly states the calling contract — pass a mask covering the sky, and chain the result via images[0].asset_key to the next image.* tool or download via download_url. It also tells the agent what to do on each refusal. There are no explicit exclusions naming when to prefer image.inpaint or image.replace_background instead.

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