Skip to main content
Glama
new-outlook-mcp

new-outlook-mcp

by michalhron

get_thread

Read-onlyIdempotent

Retrieve the full email conversation containing a specific message, ordered oldest first, using Message-ID, references, Outlook conversation ID, or normalized subject fallback.

Instructions

Get the conversation containing a message, oldest first. Uses Message-ID/References/In-Reply-To, the Outlook conversation id, and falls back to the normalized subject.

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": "get_thread"
  }
}

Input Schema

NameRequiredDescriptionDefault
email_idYesArchive id or Internet Message-ID of any message in the thread
body_charsNoBody characters per message
max_messagesNo
subject_fallbackNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the matching strategy (Message-ID/References/In-Reply-To, then Outlook conversation id, then normalized subject), which explains why results can be broader than expected. It stops short of flagging the false-positive risk of subject fallback or how missing/duplicate messages are handled.

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?

Two tight sentences, front-loaded with the ordering guarantee before the matching mechanics. Nothing is redundant, though the second sentence reads as one dense clause rather than structured detail.

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?

For a simple 4-parameter read tool with full annotation coverage and no output schema, the description is close to sufficient. Gaps remain around what the result looks like (message count limits, truncation, behavior when the thread cannot be resolved), which matter for an agent assembling a conversation.

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 only 50%, so the description has to carry weight; its mention of falling back to the normalized subject meaningfully explains the subject_fallback toggle. email_id, body_chars and max_messages remain undocumented in prose, and the truncation behavior of body_chars is not described, so it does not fully close the gap.

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?

Specific verb and resource: 'Get the conversation containing a message, oldest first' tells the agent exactly what is returned and in what order. It implicitly contrasts with get_email (single message), though it never names a 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?

Usage is implied by the resource itself – an agent can infer to call this when it wants the surrounding thread rather than one message. But there is no explicit when-to-use/when-not guidance, no mention of the alternative (get_email, search_emails), and no statement of what happens when the message is absent.

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