Skip to main content
Glama
new-outlook-mcp

new-outlook-mcp

by michalhron

create_draft

Open a prefilled Outlook draft for user review even when another app is the default mail client; it never sends, letting users verify recipients, body, and attachments before manual sending.

Instructions

Open a prefilled draft in Outlook, even if another app is the default mail app. It never sends: the user reviews and sends the draft manually. route says how it was opened and attachments_in_draft whether the files really are in it. If that is false, tell the user to drag them in from Finder.

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>"
    },
    "name": "create_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
ccNo
toYesRecipient addresses
bccNo
bodyNoPlain-text body
subjectNo
attachmentsNoAbsolute paths of local files to attach

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already mark it non-read-only, open-world, non-idempotent and non-destructive, and the description adds real value on top: it explicitly states the tool never sends and that the user completes the action manually, and it surfaces return fields (route, attachments_in_draft) even though no output schema exists. It stops short of covering the non-idempotent consequence (repeated calls opening multiple drafts) or what happens if Outlook is unavailable.

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?

Four tight sentences, front-loaded with the core action, then the never-sends guarantee, then the return-field caveat and the corrective instruction. Nothing is padded, though the return-field sentence is slightly compressed to the point of being terse.

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 6-parameter, no-output-schema mutation tool this covers the essentials: what it creates, that it is user-completed, and how to interpret the two result flags that matter for attachments. The remaining gap is failure modes (Outlook missing, duplicate drafts from repeated calls).

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 50%: to, body and attachments are documented in the schema, while cc, bcc and subject carry no descriptions. The description only gestures at attachments ('whether the files really are in it') and adds no format or constraint meaning for the undocumented recipient/subject fields, so it neither compensates nor regresses.

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?

The first sentence gives a concrete verb and resource ('Open a prefilled draft in Outlook') plus the notable scope caveat that it forces Outlook even when another mail app is default. An agent can tell this composes a new outbound draft rather than routing a reply, though it never explicitly contrasts itself with create_reply_draft or create_event_draft.

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?

Usage is implied rather than stated: composing a user-reviewed draft, never a send. It does supply an actionable fallback rule ('If that is false, tell the user to drag them in from Finder'), but it never names when to prefer this over the reply/event draft siblings.

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