Access email attachments using message and attachment IDs. This tool retrieves file content as plain text or provides base64 data for binary files, supporting downloads up to 8MB.
Downloads one attachment of a message. Returns text for text-like files (txt, csv, html, json, ics) and base64 data (up to 8MB).
| Name | Required | Description | Default |
|---|---|---|---|
| messageId | Yes | ||
| attachmentId | Yes | attachmentId from get_message (zero-based index). |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: text decoding for txt/csv/html/json/ics, base64 for everything else, and an 8MB ceiling. That's real context an agent needs before calling, though error behavior is unstated.
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?
Two sentences, front-loaded with the action and scoped by the second on return format. No filler, no repetition of the name or title.
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 simple two-parameter read tool with no output schema, the description covers the operation, the return encoding rule, and the size limit – essentially everything needed to call it and interpret the result correctly.
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 50%: attachmentId is documented, messageId is not. The description adds no parameter-level detail, so the undocumented messageId carries on being self-evident from its name only. Baseline 3 is appropriate given partial schema coverage and no compensating description text.
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 ('Downloads') and resource ('one attachment of a message'), which cleanly separates it from get_message and other sibling tools. It doesn't explicitly name a sibling alternative, but the resource is unambiguous enough that an agent can pick it out of the list.
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 implied by 'one attachment of a message' and the schema note pointing at get_message as the source of the attachmentId. There is no explicit when-to-use or when-not statement, and no mention of what to do if the attachment is too large or unsupported.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.