Outlook MCP Server

Overview Schema Source Related Servers Discussions Admin

send_draft

Sends an approved email draft created by create_draft or create_reply_draft using its draft_id. Use only after explicit user approval; sending cannot be undone.

Instructions

Send a draft made by create_draft or create_reply_draft. Cannot be undone. Call it only after the user has explicitly approved that specific draft in this conversation. draft_id comes from the tool that created the draft.

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": {
      "draft_id": "<draft_id>"
    },
    "name": "send_draft"
  }
}

Input Schema

Name	Required	Description	Default
`draft_id`	Yes

Output Schema

Name	Required	Description	Default
`result`	Yes

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?

No annotations exist, so the description carries the full behavioral burden, and it does disclose the single most important trait: the action cannot be undone. It stops short of covering delivery semantics or permission/auth requirements, but irreversibility plus the approval gate is the critical disclosure for this tool.

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 short sentences, front-loaded with the action and its irreversibility, then the approval precondition, then the parameter note. Nothing is redundant or padded.

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 destructive one-parameter tool with an output schema already describing returns, the description covers the essentials: what it does, that it is irreversible, when it is authorized, and where the argument comes from. Only edge behavior (failure modes, delivery timing) is left unstated, which is minor here.

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 coverage is 0% and the single parameter is undocumented in the schema, so the description must compensate: it explains that draft_id comes from the tool that created the draft, giving the agent a concrete source for a valid value. It does not specify the ID format, but provenance is the meaningful addition.

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 opens with a specific verb and resource ("Send a draft") and immediately scopes it to drafts produced by create_draft or create_reply_draft, which cleanly separates it from update_draft, create_forward_draft, and the other draft siblings.

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?

It states an explicit gating condition — call only after the user has explicitly approved that specific draft in this conversation — which is exactly the guidance an agent needs before firing an irreversible send. It also explains the provenance of draft_id, so the agent knows which upstream tool to call first.

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