Skip to main content
Glama
EveryInc

google-workspace-mcp-server

by EveryInc

Create Gmail Draft

gmail_create_draft

Create a Gmail draft with recipients, subject, body, CC, BCC, and reply-to. Draft is saved but not automatically sent.

Instructions

Create a new email draft in Gmail. The draft is saved but NOT sent automatically.

Args:

  • to (string[]): Array of recipient email addresses (required)

  • subject (string): Email subject line

  • body (string): Email body content (plain text or HTML depending on content_type)

  • content_type (string, optional): MIME content type - "text/plain" (default) or "text/html"

  • cc (string[], optional): Array of CC recipient email addresses

  • bcc (string[], optional): Array of BCC recipient email addresses

  • reply_to_message_id (string, optional): Message ID to reply to (for creating reply drafts)

Returns: { "draftId": string, "messageId": string, "threadId": string }

Examples:

  • Simple draft: to=["bob@example.com"], subject="Hello", body="Hi Bob!"

  • Reply draft: to=["bob@example.com"], subject="Re: Meeting", body="Sounds good!", reply_to_message_id="abc123"

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
toYesArray of recipient email addresses
subjectYesEmail subject line
bodyYesEmail body content (plain text or HTML depending on content_type)
content_typeNoMIME content type for the email body (default: text/plain)text/plain
ccNoArray of CC recipient email addresses
bccNoArray of BCC recipient email addresses
reply_to_message_idNoMessage ID to reply to (for creating reply drafts)
Behavior5/5

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

Annotations indicate non-readOnly, non-destructive, non-idempotent, and open-world. The description aligns perfectly, adding that the operation creates a draft (write operation) without sending, and details the return schema (draftId, messageId, threadId). This provides complete behavioral transparency beyond annotations.

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?

The description is well-structured with Args, Returns, and Examples sections, and the key purpose is front-loaded. While comprehensive, it is slightly lengthy but every part contributes to clarity. Could be tightened slightly without losing information, but overall efficient.

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?

Given 7 parameters (3 required), no output schema, and no nested objects, the description covers all necessary information: parameter details, return structure, and usage examples. The agent has everything needed to correctly invoke the tool and interpret results.

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. The description adds value by listing all parameters in a clear Args style, specifying defaults (e.g., content_type defaults to text/plain), and providing concrete examples that illustrate usage patterns (simple draft and reply draft). This enhances understanding beyond the schema alone.

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 clearly states 'Create a new email draft in Gmail' and emphasizes that the draft is saved but NOT sent automatically. This specific verb+resource combination distinguishes it from any potential sending tools, though none are listed as siblings. The purpose is unmistakable.

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?

The description explicitly notes that the draft is not sent, guiding agents to use this tool when they intend to save a draft for later. However, it does not explicitly contrast with alternative tools for sending or editing drafts, nor does it advise when not to use. The guidance is clear in context but could be more explicit about alternatives.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/EveryInc/google-workspace-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server