Read Attachment

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

The annotations already declare this a safe, idempotent, non-destructive read, so the description's added value is in the mechanics: text-like payloads are downloaded server-side and inlined, while binary or oversized payloads return metadata plus a fresh download link. That is genuine behavioral context an agent could not derive from the annotations. It stops short of describing the failure modes (expired links, permission denied on multi-mailbox credentials) that would make it fully transparent.

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 the usage trigger and then the branching behavior, with no filler. The middle clause about not needing a generic web_fetch tool is somewhat tangential but does usefully preempt a wrong tool choice.

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?

An output schema exists, so return values need not be spelled out, and the description covers the main branch point (text inline versus metadata plus link). For a five-parameter, read-only tool this is close to complete; only the mode-switching behavior and multi-mailbox credential handling remain unaddressed in prose.

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 description coverage is 100%, so all five parameters including mode, mailbox_id, and max_text_bytes are already documented in the schema, establishing the baseline of 3. The description gestures at size limits ('oversized attachments') but does not explain the mode values or how max_text_bytes interacts with the inline-versus-link decision.

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 pairs a specific verb ('read') with a specific resource ('message attachment') and states what is retrieved ('the attachment contents'). It clearly differs from a search or list tool, though it never names the closely-related siblings mailbox_get_attachment, mailbox_get_attachment_text, or mailbox_request_attachment_text, so fine-grained differentiation is left implicit.

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 a precondition and trigger ('after finding a message attachment when you need the attachment contents'), which is real usage guidance. However, with at least three sibling tools covering attachment retrieval, there is no explicit statement of when to pick this one over get_attachment or request_attachment_text, leaving the routing to inference.

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