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

Annotations only cover the generic mutation profile (readOnly=false, idempotent=false, destructive=false). The description adds substantive behavior: a persisted generation is created, account entitlements (credits) are consumed, and the operation is asynchronous with get_generation as the completion path.

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?

Three tight sentences: capability, then what gets created, then the async follow-up. Front-loaded and no filler, though 'ready for print' is mild marketing that adds little operational value.

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?

Output schema exists, so return values need no explanation, and the async contract is handled via the get_generation pointer. The main residual gap is the anyOf source structure, which the description only partially covers.

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 0% and the single 'source' param is a two-branch anyOf (upload_id vs generation_id) with no documentation in the schema. The phrase 'an image already in the account' hints that both uploads and generations are valid sources, but the required type discriminator and uuid format go unexplained.

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: increase resolution/clarity of an image, producing a saved generation. Sibling differentiation is implicit at best (doesn't contrast with vectorize_image, edit_image, or restore_photo), but the operation itself is unambiguous.

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?

Gives real context: the source must be 'an image already in the account' (vs. a local file or URL), and it tells the agent to call get_generation to await the result — a concrete next-step instruction. No explicit when-not or named alternative, so it stops short of a 5.

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