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

Beyond the annotations (which only say non-readOnly, non-destructive, non-idempotent), the description discloses that the link is short-lived with a 60-minute validity, accepted formats (JPG/PNG/WebP), a default of 10 and cap of 20 files, member-only access, and that it performs no attachment. These are exactly the operational constraints an agent needs and none of them are in the structured fields.

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?

It is front-loaded with the purpose and the workflow ordering, and every clause carries information (format limits, expiry, member restriction, non-attachment caveat). It is a dense single paragraph rather than clearly segmented bullets, which slightly hurts scanability for an agent parsing multiple constraints.

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 three-parameter tool with no output schema, the description covers the full lifecycle: creating the link, handing the URL to the user, retrieving upload ids via getUploadSessionTool, and finalizing with setProductImages. Constraints, validity window, and access requirements are all present.

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 reinforces the default and hard cap on maxFiles and clarifies that the link's scope is the project with a member requirement. It adds little beyond the schema definitions of productId and projectId, so it falls short of a 5.

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 specific verb and resource ('Get a short-lived link where the user uploads product pictures') and immediately distinguishes itself from media-reading tools by noting 'you do not get the bytes of attachments'. It is also clearly separable from uploadMediaFromUrlTool and setProductImagesTool, which it names.

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 triggering condition ('when the user has pictures you cannot read'), the follow-up workflow ('call getUploadSession with the token to get the upload ids, then setProductImages'), and the excluded case ('the link only adds pictures to the media library — it attaches nothing'). An agent has no ambiguity about when to pick this tool versus the image-setting siblings.

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