Skip to main content
Glama
mpalermiti

outlook-mcp

by mpalermiti

outlook_download_attachment

Idempotent

Download an email attachment from Outlook and save the decoded bytes to a file inside the configured attachments directory.

Instructions

Download an attachment and write the decoded bytes to save_path on the host.

save_path is resolved inside the configured attachments directory (attachments_dir, default ~/.outlook-mcp/attachments) — a bare filename lands there; a path outside it is refused. Same directory for reads and writes.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
save_pathYes
message_idYes
attachment_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.11.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations only give the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false); the description adds real context the annotations cannot: bytes are decoded before writing, save_path is sandboxed to attachments_dir, and out-of-directory paths are refused. It stops short of auth requirements or overwrite/error behavior, but the write-scope disclosure is substantive.

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?

The core action is front-loaded in the first sentence, with the save_path constraints following. All sentences carry information, though the path-sandboxing detail is slightly belabored.

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

Completeness3/5

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

For a 3-required-param mutation with 0% schema coverage and no output schema, the save_path behavior is well covered, but the two identifier parameters and the failure/overwrite outcome are left unspecified, leaving gaps for correct invocation.

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 is 0%, so the description must carry all three parameters, but it only explains save_path (bare filename resolution, sandbox refusal). message_id and attachment_id remain entirely undocumented in both schema and prose.

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?

States a specific verb (Download) and resource (an attachment) plus the concrete effect (write decoded bytes to save_path on the host). This differentiates it cleanly from siblings like outlook_list_attachments (read metadata) and outlook_attach_to_draft (upload direction).

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

Usage Guidelines2/5

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

The description never says when to prefer this tool or how to obtain message_id/attachment_id (e.g. via outlook_list_attachments), nor any exclusions. Usage is only inferable from the verb, with no explicit routing guidance.

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