Open an attachment

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

Annotations only declare readOnly and closed-world; the description adds what annotations cannot: the return shape (images for photos, text for PDFs, images only for pages lacking a text layer) and the critical behavioral trait that tall photos/pages arrive in overlapping parts that must be read in full before extracting figures. That is exactly the 'beyond annotation' context an agent needs.

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?

Three short sentences, front-loaded with purpose followed by output shape then the pagination caveat. Every sentence carries actionable information; nothing is padded.

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?

With no output schema, the description does the necessary work of describing what comes back and how large documents are chunked. It is nearly complete for a read tool whose annotations already cover safety, though it omits error behavior (missing file, page out of range) and whether multiple attachments can be fetched at once.

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 schema already documents id, file, part, pages and as_images in detail. The description reinforces the 'overlapping parts' semantics of `part` and hints at page-by-page reading, but adds no format or constraint detail beyond what the schema provides, 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 ('Open a photo or PDF attached to a note') and gives concrete examples (invoice, receipt, scan). It does not explicitly distinguish itself from the sibling get_page_image, which likely overlaps on 'image of a page', so it falls short of full sibling differentiation.

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?

Usage is clear contextually: this is how you pull an attachment referenced by a note. It even gives tactical guidance ('read them all before taking figures, and count a repeated line once'), but it never says when to prefer get_page_image or read_note instead, and does not state prerequisites such as where the id/file values come from.

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