Skip to main content
Glama
langmail-mcp

langmail-mcp

Official
by langmail

Get draft

get_draft
Read-onlyIdempotent

Read a staged draft's sender, recipients, subject, threading, body preview and attachment blobIds to confirm what was staged before sending or to preserve files when updating attachments.

Instructions

Read a staged draft back: its sender, every recipient including bcc, subject, whether it is threaded onto a conversation, the first 500 characters of the body, and every attached file with its blobId. Use this to confirm what was staged before sending — especially for a draft you did not write yourself — and to get the blobIds update_draft needs to keep those files when it replaces the attachment list. For messages that have already been sent or received, use get_email.

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": "get_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.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already establish that this is a non-destructive, idempotent read. The description adds meaningful behavioral context beyond that, notably that the body is limited to the first 500 characters and that attachments are returned with blobId. It does not discuss error behavior for missing drafts, but the key return-shape expectations are clear.

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?

The description is front-loaded with the return contents, then moves immediately into usage guidance and the sibling alternative. Despite being dense, every clause contributes either a returned field, a usage condition, or a routing instruction.

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 carries the burden of explaining what comes back, and it does so specifically: sender, all recipients including bcc, subject, threading, truncated body, and attachments with blobIds. Given the single fully documented parameter and the read-only annotations, this is complete enough for an agent to call it correctly.

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 coverage is 100%, so the draftId parameter is already fully documented as coming from create_draft, update_draft, list_drafts, or a Drafts search result. The description adds no further direct meaning for draftId, though its explanation of blobIds relates to a downstream update_draft call rather than to this parameter.

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 description gives a specific verb and resource ('Read a staged draft back') and then enumerates the concrete fields returned, including recipients with bcc, threading status, truncated body, and attachments with blobId. It explicitly distinguishes itself from get_email for messages already sent or received.

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?

It states exactly when to use the tool: to confirm what was staged before sending, especially for drafts not written by the agent. It also names the direct alternative, get_email, for sent or received messages, and explains the related need to obtain blobIds for update_draft.

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