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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false), the description discloses the asynchronous interaction model (card is open, agent must wait), where the artifacts land (media library, not the conversation), that stored addresses return into the conversation context, and a concrete 30-minute validity window. These are exactly the traits an agent cannot infer from 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?

The capability and its destination are front-loaded, and every clause carries operational information (trigger, wait state, follow-up tool, expiry). It is dense and slightly run-on across a single long paragraph, but little 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?

For a single-parameter, no-output-schema tool with async UI semantics, the description covers the full lifecycle: how the card is presented, what happens on completion, the required agent behavior while waiting, the follow-up tooling, and the 30-minute expiry. Nothing needed to invoke 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?

There is a single optional parameter and schema description coverage is 100%, with the schema already giving an example ('Photos for Vanilla candle', 'Your logo'). The description adds no further meaning about the purpose field, so the baseline of 3 applies.

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 uses a specific verb and resource ('Open a card in the chat where the merchant picks or drags pictures') and immediately states the destination ('each one goes straight into the shop's media library without passing through the conversation'). It is clearly distinguishable from media_upload ('files cannot be passed to media_upload') and from products_add_image, which is described as the downstream step.

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 explicit trigger conditions ('whenever the merchant wants to add pictures they have with them and did not attach, or when files cannot be passed to media_upload') and names the alternative tool that is not appropriate in that case. It also prescribes the follow-up sequence (tell them the card is open and wait; then use products_add_image, or propose_plan for several).

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