Skip to main content
Glama
uth-mail-mcp

uth-mail-mcp

by fotispetrou

download_attachment

Save a single email attachment to disk for local access. Specify the message UID and attachment index to retrieve the file, which is stored in ~/Downloads/uth-mail/ unless another directory is set.

Instructions

Save one attachment of a message; index is its number in get_message. Saves under ~/Downloads/uth-mail/ unless a destination directory is given, and returns the local file path.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "uid": "<uid>",
      "index": "<index>"
    },
    "name": "download_attachment"
  }
}

Input Schema

NameRequiredDescriptionDefault
uidYes
indexYes
folderNoinbox
destinationNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare this is a non-read-only, non-destructive, non-idempotent write, so the safety bar is partly covered. The description adds real context the annotations lack: the default output location (~/Downloads/uth-mail/) and the returned local path. It omits overwrite behavior and failure modes, which matter for a non-idempotent file write.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two compact sentences with no filler, and the key dependency (index comes from get_message) is front-loaded. Nothing is redundant with the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, stating that it returns the local file path is a valuable inclusion, and the default landing directory answers the main question an agent would have. A non-idempotent write tool would ideally also disclose overwrite and error behavior, but the essentials are present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the burden, and it compensates for only part of it: `index` is defined as the attachment's number in get_message and `destination` is framed as an optional directory. `uid` and `folder` receive no explanation beyond the schema's bare integer/string types and inbox default.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb and resource ("Save one attachment of a message") and ties the tool to its data source by referencing get_message for the index. It is distinguishable from siblings like get_message or send_draft, though it never explicitly names an alternative download path.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It implies the required workflow -- obtain the index from get_message first -- which is genuine usage guidance. It does not say when not to use this tool, what happens if the file already exists, or how it relates to any other retrieval tool.

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