Outlook MCP Server

Overview Schema Source Related Servers Discussions Admin

move_messages

Move one or more Outlook messages by ID to a specified folder, with a confirmation count to preview the move before applying it.

Instructions

Move messages by id to a folder (any count; sent to Graph 20 per request).

Prefer the specific tool when one fits: archive_messages for Archive, delete_messages for Deleted Items, report_junk when the user wants the sender blocked rather than just filed in Junk. destination: inbox, archive, junkemail, deleteditems, or a folder id from list_folders / create_folder. confirm_count: must equal the number of ids. Call without it first, show the user what would move, then call again with it. Moved messages get new ids, returned as new_message_ids; the old ids stop working.

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_ids": "<message_ids>",
      "destination": "<destination>"
    },
    "name": "move_messages"
  }
}

Input Schema

Name	Required	Description	Default
`destination`	Yes
`message_ids`	Yes
`confirm_count`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 9, 2026

TDQS

A4.6/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and mostly discharges it: it discloses the batching behavior (20 per Graph request), the irreversible id churn ('Moved messages get new ids... the old ids stop working'), and the returned field new_message_ids. It stops short of stating what happens on a count mismatch, whether a partial failure rolls back, or any permission requirement.

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?

Front-loaded with the action and the routing rule, then parameter guidance — every sentence earns its place, and the id-invalidation warning is a valuable closer. Minor deduction: the parameter block is formatted as ragged prose fragments rather than clean lines, and 'sent to Graph 20 per request' is a mild implementation detail.

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?

Covers what an agent needs for a 3-param mutation tool with no annotations and no output schema: destination vocabulary, confirmation protocol, sibling routing, batching limits, and the return field. Nothing material is missing aside from error-path behavior.

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

Parameters4/5

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

Schema description coverage is 0%, so the description must supply all parameter meaning, and it does for destination (enumerates inbox, archive, junkemail, deleteditems, or a folder id from list_folders/create_folder) and confirm_count (must equal the number of ids, with the intended call sequence). message_ids is only implied via 'by id' and the count constraint, which is the one remaining gap.

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 and resource ('Move messages by id to a folder') plus the operational scope ('any count; sent to Graph 20 per request'). It then names the sibling tools it is not (archive_messages, delete_messages, report_junk), so an agent can route without opening other schemas.

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

Usage Guidelines5/5

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

Explicitly names three alternative tools and the exact condition each one wins under ('archive_messages for Archive', 'report_junk when the user wants the sender blocked rather than just filed in Junk'). It also prescribes a concrete two-call workflow: call without confirm_count, show the user, then call again with it.

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