attachment

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

Goes well beyond the readOnlyHint/openWorldHint annotations by disclosing exact return behavior per file type (images under 5 MB as pictures, PDFs limited to first 50 pages, text up to 50,000 characters, other files return only name/type/size) and error behavior for a nonexistent ID. 'Changes nothing' reinforces, rather than merely repeats, the safety profile.

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 action and ID format, then limits, then the alternative tool, then side effects and error behavior. No sentence is filler despite covering a lot of ground.

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 fully compensates by describing what is returned for each file class, including size/page/character caps, plus the failure mode for bad IDs. Nothing needed to call this 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 the 'id' property already documents the format and that thread displays these IDs, so the description's ID example is largely redundant. Baseline 3 applies since the schema carries the parameter semantics.

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 one attachment of an email by its ID') and gives a concrete ID format example ('INBOX#1234#0'). An agent can distinguish this from siblings like thread, emails, and draft without opening any 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?

Explicitly routes the agent to an alternative: 'To put it on a new email instead, use draft(attach_from=[id])'. It also names the source of the ID ('thread shows these IDs'), covering both when to use this tool and which sibling to pick when the goal differs.

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