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

Annotations only say readOnlyHint=false, destructiveHint=false, openWorldHint=true, so the description usefully adds that the source is copied into their own storage so it cannot break later, and that storage normalizes to WebP and is content-hashed. That is real behavioural context beyond the annotations (durability, format normalization, implied dedup), though nothing is said about size limits, auth requirements, or failure modes.

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 the purpose before any parameter detail, then the input rule, then the caveat, then the downstream hand-off. Every sentence carries information the agent needs; nothing is padding.

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?

No output schema exists, and the description compensates by stating what comes back (a url) and exactly what to do with it. For a 3-parameter upload tool with a required projectId, plus storage-behaviour disclosure and the attached-image caveat, nothing an agent needs to call it 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 100%, so the baseline is 3, but the description adds a constraint the schema cannot express: EXACTLY ONE of url or data, since there is no oneOf in the schema. It also sharpens `url` (the image file's own url, not a page url) and `data` (base64 or data: URI for generated bytes).

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?

"Store a picture in UiChemy and get back a url for an image slot" gives a specific verb (store/upload) plus resource (image) and the contract on the other side (a url for a slot). It is clearly distinguishable from neighbours like crop_image, edit_image_masked, and set_images, which transform or place images rather than ingest them.

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 states the selection rule between the two mutually exclusive inputs and the condition for each (url for an already-hosted file, data for bytes you generated). It also names a when-not case — an image the user attached in chat cannot be sent as base64, ask for its url — and routes the output to uichemy_set_images or create_project's `images`.

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