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

With no annotations, the description carries the full burden of behavioral disclosure, and it does so thoroughly: presigned URLs expire in 1 hour, the HTTP method is PUT, the server rejects non-conforming images on submit, the server neither converts nor crops, dimension/ratio tolerance is specified, and the description's ratio is not enforced. This goes well beyond the input schema and gives an agent an accurate mental model of the behavior.

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?

The description is dense and front-loaded, starting with the core action before moving to requirements, constraints, and exclusions. Every sentence conveys a distinct requirement and none is filler, though the paragraph is long and the all-caps phrases make it less polished than it could be.

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?

For a nuanced upload tool with no annotations, this description is remarkably complete: it covers URL expiry, HTTP method, accepted format, aspect ratio tolerance, recommended dimensions, maximum size, conversion command, rejection behavior and error code, where the path is valid, where constraints are not enforced, and the alternative for videos. An output schema is present, so the return-value description is sufficient without enumerating fields.

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?

The only parameter, count, is already fully documented in the schema with type, range (1-21), and default (1), and schema coverage is 100%. The description merely repeats 'Ask for several at once with count', adding no meaningful semantic detail beyond the schema, so the baseline score of 3 is appropriate.

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 opens with a precise verb and resource: it issues presigned URLs for PUT-ing WebP images and returns each one's path. It further narrows the purpose by stating which fields the path works in (gallery, bannerUrl, inline description) and by explicitly excluding videos, which differentiates it from sibling upload tools like evidence_upload_link and zip_upload_link.

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?

The description gives clear context for when to use the tool: for WebP images intended for gallery, banner, or description placement, with the count parameter for batching. It also provides a when-not case ('Videos do NOT go through here') and points to the alternative mechanism (YouTube links in youtubeLinks). It does not explicitly contrast with the other upload sibling tools, but the domain is sufficiently clear.

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