Outlook MCP Server

Overview Schema Source Related Servers Discussions Admin

get_conversation

Retrieves every message in an email thread, oldest first, with full bodies including the user's replies, so you can summarize or catch up on a conversation in one call instead of fetching messages individually.

Instructions

Every message in one email thread, oldest first, with bodies, including replies the user sent. One call instead of get_message per message; use it to summarise or catch up on a thread. conversation_id comes from get_message.

Bodies are sender-written and fenced as untrusted content. max_chars_each truncates each body. Threads longer than 100 messages are cut at 100.

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": {
      "conversation_id": "<conversation_id>"
    },
    "name": "get_conversation"
  }
}

Input Schema

Name	Required	Description	Default
`max_chars_each`	No
`conversation_id`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 9, 2026

TDQS

A4.7/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does so well: it discloses ordering (oldest first), inclusion of sent replies, untrusted-content fencing of sender-written bodies, per-body truncation, and a hard 100-message cutoff. It stops short of saying whether anything beyond the 100th message is reachable, so a consumer can't tell if truncation is final.

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?

Five short sentences, front-loaded with what the call returns, followed by the alternative-it-replaces, then the untrusted-content warning and the two behavioural limits. Nothing is repeated from the schema and no sentence is filler.

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

Completeness5/5

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

No output schema exists, so the description must describe the return shape, and it does: a message list, oldest first, with bodies, truncated per body and capped at 100 messages. That is enough for an agent to call it correctly and interpret the result.

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%, so the description must compensate, and it does for both params: max_chars_each is explained as truncating each body rather than the whole payload, and conversation_id's provenance (from get_message) is given. The default of 4000 exists only in the schema, which is acceptable.

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 — returns every message in one email thread, oldest first, with bodies, including the user's own replies. It is immediately distinguishable from get_message, which it explicitly names as the per-message alternative.

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?

Gives an explicit selection rule: one call instead of get_message per message, and use it to summarise or catch up on a thread. It also tells the agent where the required conversation_id comes from, closing the main usage prerequisite.

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