Outlook MCP Server

Overview Schema Source Related Servers Discussions Admin

permanently_delete_messages

Permanently deletes Outlook messages by ID with no recovery; use only when a user explicitly asks to purge email. Confirm the message IDs and count first to prevent accidental loss.

Instructions

Delete messages by id with no recovery from Outlook. Use only when the user explicitly asked to purge; otherwise use delete_messages.

confirm_count: must equal the number of ids; call without it first and show the user the list.

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": {
      "message_ids": "<message_ids>"
    },
    "name": "permanently_delete_messages"
  }
}

Input Schema

Name	Required	Description	Default
`message_ids`	Yes
`confirm_count`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 9, 2026

TDQS

A4.4/5.0

Behavior4/5

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

With no annotations at all, the description carries the full burden and does disclose the most important trait: the operation is irreversible ('no recovery'). It also prescribes a two-step confirmation protocol. It stops short of stating permission requirements or what the confirmation-free call actually returns, which keeps it from a 5.

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?

Front-loads the destructive nature and the sibling alternative in the first two clauses, then attaches the parameter rule compactly. Every sentence earns its place with no filler.

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 a destructive, annotation-free, no-output-schema tool, the description covers the essentials: irreversibility, the alternative, and the count-confirmation workflow. The remaining gap is what the pre-confirmation call returns and where ids come from, but the agent can still call it safely.

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

Parameters3/5

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

Schema description coverage is 0%, so the description must compensate. It fully explains confirm_count (must equal the number of ids, and that the first call should omit it), but message_ids is left as just 'ids' with no format or provenance hint (e.g. from search_message_ids). Partial compensation only.

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 ('Delete messages by id') plus the crucial scope fact that there is 'no recovery from Outlook', and explicitly contrasts itself with the sibling delete_messages. An agent can pick this apart from the softer delete tool without opening either schema.

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 when-to-use gate ('Use only when the user explicitly asked to purge') and names the alternative ('otherwise use delete_messages'), which is the exact decision point an agent faces among the many delete/archive siblings.

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