workspace-mcp

Draft Gmail Message

draft_gmail_message

Create draft emails in Gmail with support for attachments, alias addresses, and reply threading. Compose new messages or reply to existing threads.

Instructions

Creates a draft email in the user's Gmail account. Supports both new drafts and reply drafts with optional attachments. Supports Gmail's "Send As" feature to draft from configured alias addresses.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`user_google_email`	Yes	The user's Google email address. Required for authentication.
`subject`	Yes	Email subject.
`body`	Yes	Email body (plain text).
`body_format`	No	Email body format. Use 'plain' for plaintext or 'html' for HTML content.	plain
`to`	No	Optional recipient email address.
`cc`	No	Optional CC email address.
`bcc`	No	Optional BCC email address.
`from_name`	No	Optional sender display name (e.g., 'Peter Hartree'). If provided, the From header will be formatted as 'Name <email>'.
`from_email`	No	Optional 'Send As' alias email address. Must be configured in Gmail settings (Settings > Accounts > Send mail as). If not provided, uses the authenticated user's email.
`thread_id`	No	Optional Gmail thread ID to reply within.
`in_reply_to`	No	Optional RFC Message-ID of the message being replied to (e.g., '<message123@gmail.com>').
`references`	No	Optional chain of Message-IDs for proper threading.
`attachments`	No	Optional list of attachments. Each can have: 'url' (fetch from URL — works with MCP attachment URLs from get_drive_file_download_url / get_gmail_attachment_content), OR 'path' (file path, auto-encodes), OR 'content' (standard base64, not urlsafe) + 'filename'. Optional 'mime_type'. Optional 'content_id' (string) makes the attachment inline-rendered: it lands in a multipart/related part with `Content-ID: <content_id>` and `Content-Disposition: inline`, and the HTML body can reference it via `<img src="cid:<content_id>">` (RFC 2392). Without `content_id` the attachment is a regular multipart/mixed attachment.
`include_signature`	No	Whether to append the Gmail signature from Settings > Signature when available. Defaults to true.
`quote_original`	No	Whether to include the original message as a quoted reply. Requires thread_id. Defaults to false.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.21.3Jun 18, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already establish readOnly=false and destructiveHint=false. The description adds meaningful behavioral context beyond that: it creates a draft (not sends), supports reply drafts, includes optional attachments, and can use configured 'Send As' aliases. These details clarify the tool's effect without contradicting any annotation.

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?

Three short sentences, each delivering distinct value: primary action, key supported modes, and a specialized feature. No redundant fluff, front-loaded with the core purpose.

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?

Despite 15 parameters and an output schema, the description captures the essential functional surface: draft creation, reply support, attachments, and alias sending. The detailed schema fills in the rest. It does not mention return values, but the output schema covers that. Slightly more explicit usage guidance would push this higher, but it is complete enough for a tool with such a rich schema.

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?

The input schema already provides 100% parameter coverage, so baseline is 3. The description elevates this by connecting high-level features to specific parameters: 'reply drafts' maps to thread_id/in_reply_to, 'attachments' maps to the attachments array, and 'Send As' maps to from_email. This adds conceptual meaning beyond individual schema entries.

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 opens with a specific verb and resource: 'Creates a draft email in the user's Gmail account.' It clearly distinguishes itself from sibling send_gmail_message by emphasizing 'draft' and explicitly names key capabilities (new drafts, reply drafts, attachments, Send As).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage contexts by mentioning 'new drafts and reply drafts' and 'Send As' alias addresses, but it never explicitly states when to choose this tool over send_gmail_message or other alternatives. No exclusions or direct alternative comparisons are given, leaving the agent to infer.

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

Deploy Server