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

Annotations only cover the read-only/open-world profile; the description adds the operationally important facts an agent cannot infer: no credit cost, a 30-reads-per-day cap, accepted formats, and a size ceiling. This is exactly the kind of extra context a read tool needs.

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 dense sentences, front-loaded on purpose, then constraints, then the alternate path. The parenthetical "(model_id, or one the picture suits)" is slightly tangled, but no sentence is wasted.

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 an output schema present, return values need no explanation, and the description covers the remaining risk areas: input format/size, cost, quota, and the case where the tool shouldn't be called at all. Nothing an agent needs in order to call this correctly 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?

Schema coverage is 0%, and the description compensates well: it defines `image` as a JPEG/PNG/WebP data URL with an approximate 700 KB ceiling and a 1024px pre-scale step, clarifying the opaque maxLength of 960000. `model_id` is glossed as an optional target model ("or one the picture suits") but its format is never spelled out.

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 names a specific verb and resource ("write the prompt that would make a picture like this one") and scopes the output to an image model. It also carves out a distinct case ("for a picture already in the account, its generation's prompt is the answer"), which separates it from generate_image, edit_image, and add_captions.

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 gives a clear when-not: if the picture is already in the account, retrieve its generation's prompt instead. It also states the cost and rate limit up front, which shapes when an agent should spend a call. The gap is that the alternative is described rather than named as a sibling tool.

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