Skip to main content
Glama
new-outlook-mcp

new-outlook-mcp

by michalhron

create_reply_draft

Drafts a reply to an archived Outlook email with recipients, Re: subject and quoted original, so you can review and send it manually; it never sends automatically.

Instructions

Open a draft answering an archived email, with recipients, Re: subject and the original quoted. It never sends: the user reviews and sends it. It is a new message, not linked to the thread (in_thread is false), because Outlook offers no way to reply to a recent message by script: tell the user.

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": {
      "email_id": "<email_id>"
    },
    "name": "create_reply_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyNoPlain-text reply, placed above the quoted original
email_idYesArchive id or Internet Message-ID of the email to answer
reply_allNoAlso address the other To and Cc recipients
attachmentsNoAbsolute paths of local files to attach
include_quoteNoQuote the original below the reply

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior5/5

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

Annotations only say it is non-read-only, non-idempotent, non-destructive, and open-world. The description adds the critical, non-obvious behavior that the result is NOT a threaded reply (in_thread is false) because Outlook cannot script replies to recent messages, and instructs the agent to tell the user. That is exactly the kind of surprise an agent must know before calling.

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?

Three compact sentences, front-loaded with what is created, then the never-sends guarantee, then the threading caveat. No filler, though the final 'tell the user' clause is terse enough to read as an afterthought.

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 5-parameter mutation with annotations but no output schema, the description covers what gets created, safety (never sends), and the threading limitation. It leaves open what the call returns (a draft id to send later?), which an agent would need to chain a send step.

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 100%, so every parameter is already documented, including reply_all, include_quote, body, and attachments. The description restates the recipients/Re:/quoting behavior but adds no format, default, or edge-case detail beyond the schema, so baseline 3 applies.

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 concrete verb and resource ('Open a draft answering an archived email') plus what the draft contains: recipients, Re: subject, quoted original. It implicitly separates itself from create_draft by scoping to answering an archived email, though it never names the sibling explicitly.

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

Usage Guidelines3/5

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

The condition of use is implied by the resource phrase 'answering an archived email', and the description warns that sending is the user's job. However, it never says when to prefer create_draft over this tool, or any exclusion beyond the general 'drafts are not sent' note.

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