Skip to main content
Glama

graph_find_meeting_times

Suggests meeting times that work for attendees by scoring candidate slots from their free/busy data, so you can pick a time and book it.

Instructions

Suggest meeting times that work for the attendees.

Graph scores candidate slots from the attendees' free/busy data, so use this to pick a time and graph_create_event to book it.

Args: attendees: Attendee email addresses to fit the meeting around. duration_minutes: Meeting length in minutes (default 30). start_datetime: Start of the search window (ISO 8601). Empty lets Graph choose. end_datetime: End of the search window (ISO 8601). Empty lets Graph choose. The window is only sent when both ends are supplied. timezone: Timezone for the search window (default "UTC"). minimum_attendee_percentage: Minimum percentage of attendees that must be free (default 100). max_candidates: Maximum number of suggestions to return (default 10). user: Shared or delegated calendar owner address or user ID to act on. Empty targets your own calendar. Requires the delegated Calendars.Read.Shared or Calendars.ReadWrite.Shared permissions.

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": {
      "attendees": "<attendees>"
    },
    "name": "graph_find_meeting_times"
  }
}

Input Schema

NameRequiredDescriptionDefault
userNo
timezoneNoUTC
attendeesYes
end_datetimeNo
max_candidatesNo
start_datetimeNo
duration_minutesNo
minimum_attendee_percentageNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.10.0

TDQS

A4.4/5.0
Behavior4/5

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

No annotations exist, so the description carries the full burden and does well: it discloses that only suggestions are produced (booking is a separate call), that the time window is sent only when both ends are supplied, that `user` requires Calendars.Read.Shared/ReadWrite.Shared delegated permissions, and that empty values defer to Graph's own choices. It does not cover what happens when no slot meets the threshold, or any rate-limit/throttling behavior.

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?

Purpose and the sibling routing are front-loaded, and the Args list is scannable. Minor waste: it restates defaults already present in the schema (30 minutes, "UTC", 100, 10), which adds length without new information.

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 an 8-parameter tool with no annotations and no output schema, the description covers purpose, routing, every parameter, and auth requirements. The remaining gap is the return shape — what a suggestion contains (confidence, individual attendee availability) and what comes back when no times satisfy minimum_attendee_percentage.

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

Parameters5/5

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

Schema description coverage is 0%, so the description must carry all parameter meaning — and it documents all 8, including the non-obvious rule that the window is only transmitted when both start and end are supplied, and the permission requirement for `user`. Meaningful semantics (timezone applies to the search window, percentage is a freedom floor) are added beyond bare names.

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 ('Suggest meeting times') and immediately explains the mechanism ('Graph scores candidate slots from the attendees' free/busy data'). It also distinguishes itself from the sibling used for the next step: 'use this to pick a time and graph_create_event to book it.'

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?

Explicit routing guidance names graph_create_event as the booking follow-up, and the `user` parameter explains the delegated-calendar case with its required permissions. There is no explicit 'when not to use' (e.g., no alternatives for scheduling when free/busy lookup fails), which keeps it just 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.

Deploy Server

Other Tools