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

Annotations cover safety and idempotency, and the description adds context beyond them: it discloses the return fields (uploadId, uploadPageUrl, expiresAt), the idempotency mechanism (reuse requestId for retries), and critically the side-effect boundary ('Creating the link does not upload the chat attachment or add the item'). That last point is exactly the kind of non-obvious behavior an agent needs before calling a non-read-only tool.

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 core action and trigger, then progressively adds routing, returns, and workflow. Dense and mostly waste-free, though the 'Use this even when you can see a chat photo but cannot pass its real file reference, public URL or original bytes' clause is slightly verbose and could be tightened.

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 non-read-only tool with no output schema and nested params, the description covers purpose, routing, return values, idempotency, the side-effect boundary, and the required follow-up (show uploadPageUrl and ask the user to submit). Nothing essential for correct invocation 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 only 33%, so the description must carry meaning, and it does for two of three params: it fixes purpose to wardrobe_image_add ('one clothing item per image') and explains requestId generation/reuse semantics. The nested options.menswearOrWomenswear field is left entirely to the schema description, but overall the description meaningfully supplements the low-coverage schema.

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 and resource ('Create a secure web or installed-app image picker') and immediately distinguishes itself from add_wardrobe_item_from_image and add_wardrobe_item_from_description. An agent can tell exactly what this produces (an upload link/picker) without opening the schema.

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 explicit trigger conditions ('when the user asks for an upload link, or an image-based action cannot receive the original image directly'), names the correct sibling for the alternative path, and adds an explicit exclusion ('do not silently switch to add_wardrobe_item_from_description'). This is textbook when/when-not/alternatives routing.

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