Outlook MCP Server

Overview Schema Source Related Servers Discussions Admin

find_unsubscribable

Identify frequent senders in an Outlook folder that can be unsubscribed automatically, grouped by method, so you can review approved one-click and mailto senders before unsubscribing.

Instructions

Report which frequent senders in a folder can be unsubscribed from automatically. Read-only; the step before unsubscribe.

Groups senders by method: one_click (RFC 8058 web request), mailto (Outlook sends the unsubscribe email), link_only (a web page the user must open), none (no unsubscribe header; use create_rule) and skip (in Junk or failed authentication, where unsubscribing would confirm the address to a spammer). Senders unsubscribed earlier but still mailing after three days are flagged still_sending; those need a rule. Pass the one_click and mailto senders the user approves to unsubscribe.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "find_unsubscribable"
  }
}

Input Schema

Name	Required	Default
`scan`	No
`folder`	No	inbox
`min_count`	No
`candidates`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 9, 2026

TDQS

A4.1/5.0

Behavior4/5

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

With no annotations, the description carries the full behavioral burden and does well: it declares read-only behavior, explains the five sender categories, warns that skip avoids confirming an address to a spammer, and flags still_sending senders after three days. It does not discuss authentication, rate limits, or performance, but it discloses the key behavioral rules for a read-only classifier.

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?

The description is front-loaded with the core purpose, then organizes details by method and edge case. Its length is justified by the classification scheme, though it could be tightened slightly without losing meaning.

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?

The description explains the output categories and follow-up action, which is valuable because there is no output schema. However, with four undocumented parameters and no annotations, it leaves material gaps about input meanings and scanning limits.

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?

All four parameters have 0% schema description coverage and there are no annotations to compensate. The description only implicitly touches folder and frequency ('frequent senders') and never explains scan, min_count, or candidates, leaving most parameter meaning undocumented.

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?

The opening sentence names the specific action, resource, and scope: reporting frequent senders in a folder that can be unsubscribed from automatically. It explicitly positions the tool as read-only and as the step before unsubscribe, while the category guidance distinguishes it from unsubscribe and create_rule.

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?

The description states the workflow position ('the step before unsubscribe') and names alternatives for specific outcomes: create_rule for senders with no unsubscribe header, rules for still_sending senders, and unsubscribe for approved one_click and mailto senders. It also explains the skip condition in Junk or failed authentication, so the agent has clear when-to-use and when-not-to-use guidance.

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