Skip to main content
Glama
Google Workspace (GWS) MCP Server

Google Workspace (GWS) MCP Server

gmail_drafts_create

Create a Gmail draft for review before sending, optionally attaching it to an existing thread as a reply. Add recipients, subject, body, and CC/BCC details without sending the email.

Instructions

Create a Gmail draft. Pass threadId to attach the draft to an existing conversation (it will appear as a reply within that thread). The draft is NOT sent — open Gmail to review and send.

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": {
      "to": "<to>"
    },
    "name": "gmail_drafts_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
ccNoCC recipient(s), comma-separated
toYesRecipient(s). Comma-separated for multiple, e.g. "a@x.com, b@y.com"
bccNoBCC recipient(s), comma-separated
bodyNoPlain-text body
subjectNoSubject line. When attaching to a thread via threadId, Gmail expects the subject to match the thread (typically "Re: <original>").
htmlBodyNoHTML body. If both body and htmlBody are provided, the draft is multipart/alternative.
threadIdNoThread ID to attach this draft to. Get it from gmail_threads_list / gmail_messages_get.
inReplyToNoMessage-ID header value of the message being replied to. Improves threading robustness alongside threadId.
referencesNoReferences header value (space-separated Message-IDs of ancestor messages).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.5.0
    • removedInput schema / additionalProperties
      Removed value: -false
  2. Addedv0.1.2

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=true, and idempotentHint=false, so safety is partly covered. The description adds genuinely new behavior: the draft is persisted but not transmitted, thread-attached drafts appear as replies inside the conversation, and sending must happen out-of-band in Gmail. It does not say what identifier is returned, which is the main remaining gap.

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, front-loaded with the core action, then the threadId modifier, then the critical not-sent caveat. No redundant restatement of the name and no filler.

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?

For a nine-parameter create operation with full schema coverage, no output schema, and existing annotations, the description covers the essential behavioral facts an agent needs: it creates rather than sends, and thread attachment changes where the draft appears. Only the return value and any auth/scope requirements are unmentioned, which keeps it from a 5.

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 description coverage is 100%, so all nine parameters (to, cc, bcc, subject, body, htmlBody, threadId, inReplyTo, references) are already documented in the schema, including the multipart/alternative note and the thread subject-matching caveat. The description adds only a light gloss on threadId's visible effect, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence names a specific verb and resource ('Create a Gmail draft'), which is unambiguous and easily separable from the read-only siblings like gmail_messages_get and gmail_threads_list. It stops short of naming a contrasting sibling (e.g., a send tool), but the object is specific enough that an agent knows exactly what it produces.

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 gives clear usage context: pass threadId to make the draft a reply, and note that the draft is not sent so the user must open Gmail to review and send. There is no explicit when-not guidance or named alternative tool, but the review-then-send workflow is spelled out enough to steer behavior.

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