Outlook MCP Server

Overview Schema Source Related Servers Discussions Admin

create_draft

Creates a new Outlook email in Drafts with recipients, subject, and body so the user can review it before any send action is approved.

Instructions

Create a new email in Drafts, addressed and ready for the user to review. Nothing is sent until send_draft is called after the user approves the draft.

body: write it as you would in chat. Blank lines separate paragraphs; Markdown lists, bold, italic and links are converted to HTML so the draft looks the same in Outlook. Set html=true only for ready-made HTML. Returns draft_id (for send_draft) and web_link (for the user to open).

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": {
      "to": "<to>",
      "subject": "<subject>",
      "body": "<body>"
    },
    "name": "create_draft"
  }
}

Input Schema

Name	Required	Description	Default
`cc`	No
`to`	Yes
`body`	Yes
`html`	No
`subject`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 9, 2026

TDQS

A3.9/5.0

Behavior4/5

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

With no annotations supplied, the description carries the burden and does it reasonably well: it discloses the no-send-until-approved safety property, the Markdown-to-HTML conversion behavior for the body, the meaning of the html flag, and what the call returns. It omits permission/auth requirements and what happens with malformed recipient addresses.

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 safety guarantee, then formatting guidance, then return values. Every sentence carries information, though the formatting paragraph is dense and slightly mid-sentence-buried rather than bulleted.

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?

No output schema exists, and the description compensates by naming the returned draft_id and web_link and their downstream uses (send_draft, user review). No annotations exist, and the description covers the key mutation-safety concern. Missing only address-format expectations and error behavior.

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 must compensate; it does so for two of five parameters, explaining body formatting rules (blank lines, Markdown, links) and when to set html=true. The to, cc, and subject parameters are left entirely to self-evident naming, with no note that to/cc are arrays of addresses or that cc is optional.

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?

States a specific verb and resource ('Create a new email in Drafts') plus the resulting state ('addressed and ready for the user to review'). It explicitly contrasts with send_draft, but never mentions the sibling draft creators create_reply_draft and create_forward_draft, which an agent could easily confuse with this tool when composing a reply.

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?

Gives a clear operating context: create now, nothing is sent until send_draft is called after user approval. This establishes the workflow gate an agent needs. It stops short of explicit exclusions such as 'for replies use create_reply_draft, for forwards use create_forward_draft'.

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