Skip to main content
Glama
new-outlook-mcp

new-outlook-mcp

by michalhron

create_event_draft

Opens a new Outlook event draft (.ics) for user review and saving, without changing the calendar or sending invitations.

Instructions

EXPERIMENTAL. Open a new-event draft (.ics) in Outlook for the user to review and save. It does not add, change or delete anything in the calendar and sends no invitations.

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": {
      "subject": "<subject>",
      "start": "<start>"
    },
    "name": "create_event_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNoEnd time; for all-day events the last day. Default: 1 hour
bodyNo
startYesYYYY-MM-DDTHH:MM (local) or YYYY-MM-DD for all-day
all_dayNo
subjectYes
locationNo
timezoneNoIANA timezone for input and output times (default: this Mac's zone)
attendeesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

Adds real behavior beyond the annotations: no calendar add/change/delete, no invitations sent, and an EXPERIMENTAL status flag. This clarifies that despite readOnlyHint=false the call is non-destructive, though it omits what the call actually does on the host (launching Outlook UI) and any failure modes.

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?

Two sentences with the experimental caveat and the side-effect disclaimer front-loaded; every clause carries information and nothing is redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers purpose and safety well, but for an 8-parameter tool with no output schema it leaves the most error-prone inputs (attendees, all_day plus end interaction, timezone defaults) unexplained and does not say what the caller observes after the draft opens.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 38% (start, end, timezone documented; subject, body, location, all_day, attendees not), and the description supplies no parameter meaning at all. The .ics/review framing gives no guidance on attendees handling, all-day semantics, or timezone interaction, so it fails to compensate for the coverage gap.

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 ('Open a new-event draft (.ics) in Outlook') plus the intended consumer ('for the user to review and save'), which separates it from email-draft siblings like create_draft and from direct calendar writes.

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 framing implies the right context: use this when the event should be reviewed and saved by the user rather than committed. It does not explicitly name alternatives (e.g. a direct event-creation tool or create_draft) or state exclusion conditions, so it stops short of a 5.

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