Skip to main content
Glama
langmail-mcp

langmail-mcp

Official
by langmail

Move emails

move_emails

Move specified messages into a chosen folder so they exist only in the destination. Use message ids from search or thread results; flags stay untouched and Trash is refused.

Instructions

Move one or more messages into a folder. They are removed from every folder they were in and end up only in the destination. Use this when the user names a destination ("put this in Projects", "move it back to the inbox"). Takes message ids from search_emails or get_thread. The mailbox is resolved the same way as the search_emails mailbox filter and is never created; an unknown name returns the folders that exist. Read state and flags (to-do, starred) are untouched; use mark_emails to change them. Re-running it on the same ids is harmless. To archive use archive_emails; to delete use trash_emails — this tool refuses Trash. Reports how many messages moved and lists any id the server refused.

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": {
      "ids": "<ids>",
      "mailbox": "<mailbox>"
    },
    "name": "move_emails"
  }
}

Input Schema

NameRequiredDescriptionDefault
idsYesMessage ids to act on (1–50), as returned by search_emails or get_thread. To act on a whole conversation, pass every id get_thread lists.
mailboxYesDestination folder. The standard places — Inbox, Archive, Sent, Drafts, Junk — resolve to the folder holding that role whatever the server calls it; any other value must match an existing folder name exactly (case-insensitive). Folders are never created. Trash is not accepted here: use trash_emails.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior3/5

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

Adds substantial behavior beyond annotations: multi-folder removal semantics, mailbox names are never created and an unknown name returns the existing folders, read state/flags are untouched, and the result reports counts plus refused ids. However, "Re-running it on the same ids is harmless" sits in tension with idempotentHint=false — harmless is not the same as identical-result, so an agent may be unsure whether a repeat call is a no-op or a second side effect. Worth noting rather than flagging as a contradiction, since the description does not claim idempotency outright.

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 the action and its core effect, then alternatives, then error/return behavior — a sensible ordering with no filler sentences. Slightly dense, with several clauses packed into single sentences, and the id-provenance line partially duplicates the schema's own parameter description.

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?

With no output schema, the description still covers the return shape (count moved plus refused ids) and the main failure mode (unknown folder name returns the available folders). For a two-parameter mutation tool, nothing an agent needs in order to call it correctly is missing.

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 100%, so the baseline is 3; the description still adds value by documenting where ids come from (search_emails or get_thread, including the get_thread whole-conversation case) and by stating the mailbox resolution rule matches the search_emails mailbox filter. It stops short of restating the standard-place name resolution or the 1–50 cap, leaving those to the schema.

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 ("Move one or more messages into a folder") plus the exact semantics of the move (removed from every source folder, present only in destination). An agent can distinguish it immediately from archive_emails, trash_emails, and mark_emails, all of which are named.

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 a concrete trigger condition ("when the user names a destination") with example utterances, names the data source for ids (search_emails, get_thread), and explicitly routes away to archive_emails for archiving and trash_emails for deletion. The exclusion "this tool refuses Trash" closes the most likely misuse path.

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