ms-graph-mcp

mail_list_attachments

Read-onlyIdempotent

Retrieve attachment metadata (name, content type, size in bytes) for an email without downloading file contents, safely handling messages with large attachments.

Instructions

List the file attachments on one email — name, content type and size in bytes. Returns metadata only and never file contents, so it is safe to call on messages with very large attachments. Inline images such as signature logos are excluded. Requires Mail.Read.

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": {
      "message_id": "<message_id>"
    },
    "name": "mail_list_attachments"
  }
}

Input Schema

Name	Required	Description	Default
`message_id`	Yes	The message id to list attachments for

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Aug 5, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Despite strong annotations (readOnlyHint, idempotentHint, destructiveHint false), the description adds meaningful behavioral detail: it returns metadata only, never file contents, is safe on large attachments, excludes inline images, and requires Mail.Read. This goes beyond the annotations and helps the agent anticipate edge cases.

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

Conciseness5/5

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

Three sentences, no filler. The first sentence states the core purpose, the second adds safety/behavior, and the third notes an exclusion and a permission requirement. Every sentence earns its place.

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

Completeness5/5

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

The tool is simple (one required param, no output schema), and the description fully covers purpose, return scope (metadata only), safe usage, exclusions, and required permission. Combined with strong annotations, this is complete for the tool's complexity.

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 coverage for the single parameter (message_id) is 100%, so the schema already describes it. The description adds minimal parameter-specific meaning beyond 'one email,' which is implied by the tool name and schema. Baseline 3 applies because the schema carries the load.

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

Purpose5/5

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

The description uses a specific verb+resource ('List the file attachments on one email') and enumerates the exact fields returned (name, content type, size in bytes). It clearly distinguishes itself from sibling tools like mail_list_recent by focusing on attachments of an individual message.

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

Usage Guidelines4/5

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

The description provides clear context: use this to get attachment metadata safely even for large attachments, and notes that inline images are excluded. It does not explicitly name alternatives or state 'use X instead,' but the context is sufficient for an agent to pick this over other mail tools.

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