Outlook MCP Server

Overview Schema Source Related Servers Discussions Admin

create_reply_draft

Creates a reply or reply-all draft with the quoted thread below your text and recipients prefilled in Outlook; nothing is sent until you approve and send the draft.

Instructions

Create a reply or reply-all draft to a message, with the quoted thread below your text and the recipients filled in by Outlook. Nothing is sent until send_draft.

body: same Markdown as create_draft; line breaks are kept. Returns draft_id, subject and the recipients it will go to. Show those to the user before sending.

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>",
      "body": "<body>"
    },
    "name": "create_reply_draft"
  }
}

Input Schema

Name	Required	Description	Default
`body`	Yes
`reply_all`	No
`message_id`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 9, 2026

TDQS

A4.1/5.0

Behavior4/5

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

With no annotations, the description carries the burden and does reasonably well: it discloses that nothing is transmitted until send_draft, that the quoted thread and recipients are populated by Outlook, and that line breaks in the Markdown body are preserved. It omits where the draft lands (Drafts folder), permission requirements, and failure modes, which keeps it short of a 5.

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 capability and the safety constraint are front-loaded in the first sentence, and the follow-on lines carry only useful detail about body format and return values. The inline 'body:' label mid-paragraph is slightly ragged structurally but wastes no words.

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?

For a 3-parameter mutation tool with no output schema, the description covers the essential picture: what is created, that sending is deferred, what is returned (draft_id, subject, recipients), and that the user should confirm recipients before sending. Minor gaps remain around error behavior and how to obtain message_id, but nothing essential is missing.

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 compensate and it partially does: body semantics are described (same Markdown as create_draft, line breaks kept) and reply_all is surfaced via 'reply or reply-all'. message_id and the exact effect of reply_all on recipient computation are left undocumented.

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 (create a reply or reply-all draft to a message) and immediately distinguishes itself from siblings by naming send_draft as the separate send step. The mechanism (quoted thread below your text, recipients auto-filled by Outlook) further separates it from create_draft and create_forward_draft.

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 'Nothing is sent until send_draft' clause gives clear sequencing guidance and implicitly tells the agent this is a pre-send step. It does not explicitly say when to pick this over create_draft or create_forward_draft, but 'reply or reply-all' makes the selection condition apparent.

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