Skip to main content
Glama
langmail-mcp

langmail-mcp

Official
by langmail

Send draft

send_draft
Destructive

Sends an existing email draft to its recipients and returns the sent message ID. Confirm the recipients and body first because delivery is irreversible and already-sent drafts are refused.

Instructions

Send a draft. This delivers the message to its recipients and cannot be undone. Confirm the recipients and the body with the user before calling it unless they have already asked for the message to be sent. Sends any draft in the user’s Drafts folder, not only ones you staged — find an existing one with list_drafts, and read it back with get_draft before sending something you did not write. Use the draftId create_draft returned; editing a draft with update_draft keeps it. Returns the sent message’s id, which get_email can read back. A draft that has already been sent is refused rather than sent twice.

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": {
      "draftId": "<draftId>"
    },
    "name": "send_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
draftIdYesThe draft id, as returned by create_draft, update_draft or list_drafts — edits do not change it — or a message id from search_emails with `mailbox: "Drafts"`, which an edit replaces with the draftId it returns.
idempotencyKeyNoClient-chosen key that makes this call safe to retry: a repeat with the same key returns the first call’s answer instead of sending the message a second time. Pass one whenever the call might be retried.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, openWorldHint=true and idempotentHint=false, but the description adds meaningful context: the effect is irreversible, sending a draft that was already sent is refused rather than duplicated, and the sent message id can be read back with get_email. It does not discuss rate limits or error shapes, so it stops short of 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.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the action and its irreversibility, then conditions and tool routing. Dense but slightly elongated — the 'sends any draft... not only ones you staged' point and the list_drafts/get_draft instruction overlap somewhat.

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?

No output schema exists, and the description compensates by stating the return value (the sent message id, readable via get_email). Combined with the irreversibility and duplicate-refusal notes, an agent has everything needed to call this safely.

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 baseline is 3; however the description adds real meaning by explaining that draftId is stable across edits and that any draft in the Drafts folder can be sent, not just ones the agent staged. The idempotencyKey semantics are left entirely 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?

Names a specific verb and resource ('Send a draft') and immediately states the effect: delivery to recipients, irreversible. It is clearly distinguishable from create_draft, update_draft, get_draft and delete_draft by describing the terminal send action.

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 explicit preconditions ('Confirm the recipients and the body with the user before calling it unless they have already asked'), an exception path, and alternative tools for related flows (list_drafts to find an existing draft, get_draft to read it before sending). It also states which draftId form to pass and that update_draft preserves it.

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