Add a photo or document to an item

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

Annotations only declare readonly=false, destructive=false, openWorld=false; the description adds genuinely new behavior — asynchronous background vision processing, roughly a 20-second latency before results appear, and that suggestions are advisory rather than auto-applied. It also notes the call counts as AI actions when AI is on, which is quota-relevant context absent from the annotations. It does not cover payload size limits or failure behavior for unreadable images.

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?

Four sentences, all load-bearing: purpose first, then the async read-back flow, then the sibling exclusion, then the AI-action billing note. No restatement of the title or filler.

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 four-parameter mutation tool with no output schema, the description covers the key unknowns: that the call returns immediately while analysis is deferred, where the results surface (get_item), and how to commit them (update_item). Nothing an agent needs 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?

Schema coverage is 100% and every property is described, so the schema already carries parameter meaning; the description only reinforces the kind="document" case with concrete examples. It adds no encoding detail, default behavior, or filename semantics beyond what the schema states, so baseline 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?

States a specific verb and resource — attaches a photo or a document (receipt, manual, warranty card) to an item that already exists — and explicitly contrasts with add_item_from_photo for creating a new thing. An agent can distinguish it from the creation sibling without opening either 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 an explicit alternative for the adjacent intent ("To add a new thing from its photo use add_item_from_photo instead") and lays out the downstream workflow: wait ~20s, read results via get_item, confirm with the person, then apply with update_item. The when-to-use and what-happens-next path is fully spelled out.

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