Skip to main content
Glama
nityeshaga

google-workspace-mcp-server

by nityeshaga

Create Gmail Draft

gmail_create_draft

Create new email drafts in Gmail without sending. Specify recipients, subject, body, CC/BCC, and optionally reply to an existing message.

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
ccNoArray of CC recipient email addresses
toYesArray of recipient email addresses
bccNoArray of BCC recipient email addresses
bodyYesEmail body content (plain text or HTML depending on content_type)
subjectYesEmail subject line
content_typeNoMIME content type for the email body (default: text/plain)text/plain
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 declare it's a write operation (readOnlyHint=false, idempotentHint=false, destructiveHint=false). The description adds important behavioral context: draft is saved but not sent, content_type controls plain text vs HTML, and returns a draft ID/message ID/thread ID. No contradiction with annotations.

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?

Although detailed, the description is well-structured with Args, Returns, and Examples sections. The first sentence is a clear summary, and each section adds necessary information without unnecessary prose.

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?

The description includes return fields (draftId, messageId, threadId) since there is no output schema, covers all 7 parameters, and provides usage examples. This makes it complete for an agent to invoke the tool correctly.

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% and the description repeats parameter definitions, but it adds value through examples (simple draft and reply draft) and clarifies the reply_to_message_id purpose. This goes slightly beyond the baseline schema-only documentation.

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?

Clearly states 'Create a new email draft in Gmail' with a specific verb and resource. The description distinguishes from sibling Gmail tools (which list/get messages/threads) and clarifies the draft is not sent.

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 provides useful context: the draft is saved but not sent automatically, which tells agents when to use this tool vs a send operation. However, it does not explicitly name alternative tools or state when not to use it.

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/nityeshaga/google-workspace-mcp-server'

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