Skip to main content
Glama
Sign In
Apple Mail MCP

Apple Mail MCP

by cyberprive
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

move_to_mailbox

Destructive

Moves an email from one mailbox to another within the same account using exact folder names or @aliases like @archive or @trash. Requires confirm=true after user approval.

Instructions

[DESTRUCTIVE] Move a message from one mailbox to another within the same account.

This tool refuses without confirm=true. Always surface the planned move to the user and get explicit approval before passing confirm=true — moving a message changes user-visible state (especially when the target is Trash, Junk, or Archive). Reversible by moving back, but disruptive.

Both mailbox and target_mailbox accept either an exact mailbox name OR a localization-aware alias starting with "@": @inbox, @archive, @drafts, @sent, @trash, @junk The MCP resolves the alias against the account's actual folder names (e.g. @archive → "Archivo" on a Spanish-localized M365 account, "Archive" on iCloud English). The returned to_mailbox field is the resolved literal name so callers can log accurately.

Args: account, mailbox, id: As returned by search_messages. target_mailbox: Destination — exact name or @alias. confirm: Must be true to actually perform the move. False (default) returns a CONFIRM_REQUIRED envelope describing the action.

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": {
      "account": "<account>",
      "mailbox": "<mailbox>",
      "id": "<id>",
      "target_mailbox": "<target_mailbox>"
    },
    "name": "move_to_mailbox"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYes
accountYes
confirmNo
mailboxYes
target_mailboxYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true and non-idempotency, and the description adds substantial context beyond them: an explicit refusal gate on confirm=true, the preview envelope behavior when confirm is false, reversibility by moving back, the user-visible disruption when targeting Trash/Junk/Archive, and the resolved `to_mailbox` return field. This is exactly the extra behavioral detail the structured fields cannot carry.

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?

Front-loaded with [DESTRUCTIVE] and the confirm requirement, then the alias mechanics, then a compact Args block — a sensible ordering for an agent scanning quickly. A few phrases restate the same idea ("get explicit approval" vs. "passing confirm=true"), but nothing is wasted overall.

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?

For a 5-parameter destructive mutation with no output schema, the definition covers the gating flag, alias resolution, the preview envelope, and the one meaningful return field. Remaining gaps (permission requirements, failure modes for a nonexistent mailbox name) are minor and not blocking for correct invocation.

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?

With 0% schema description coverage, the description carries the full burden and mostly delivers: `target_mailbox` accepts an exact name or one of six enumerated @aliases with localization resolved server-side, `confirm` is explained as the gating flag with a defined default behavior, and account/mailbox/id are anchored to search_messages output. The latter three get only a one-line pointer, so semantics are thin for the identifying parameters.

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 first line states a specific verb and resource ("Move a message from one mailbox to another") plus a scoping constraint ("within the same account"). No sibling tool (search_messages, flag_message, mark_read, etc.) performs a mailbox move, so the agent can distinguish it immediately.

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?

It gives clear operational guidance: the tool refuses without confirm=true, the caller must surface the planned move and get explicit approval, and confirm=false yields a CONFIRM_REQUIRED envelope for a dry-run preview. No explicit when-not-to-use or named alternatives are offered, but the confirmation protocol is a strong usage rule.

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