Skip to main content
Glama
rajool

google-workspace-mcp

by rajool
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

gmail_draft_create

Create a Gmail draft with recipients, subject, body, and attachments. Supports reply threads by auto-quoting history and formatting plain-text lists as Gmail-compatible HTML.

Instructions

Create a Gmail draft. Returns {id, message: {...}}.

Replies: pass thread_id and nothing else. The server reads the thread and
quotes its history below your text exactly as Gmail's web Reply does, and
derives the In-Reply-To / References headers itself. So write `body` as
ONLY the new message — never paste earlier messages into it by hand, or
the recipient gets the history twice. (`in_reply_to_message_id` overrides
the derived header when you already hold the RFC822 Message-Id;
`quote_history=false` sends into the thread with no quote.)

Body format: write `body` as plain text — blank-line paragraphs,
"- " bullets, "1." / "1)" numbered lines (ASCII or Persian digits).
It goes out as multipart/alternative with a Gmail-composer-style HTML
part, so lists arrive as Gmail's real bullets/numbering and the draft
can be opened and sent from the Gmail web UI safely. Never hard-wrap
lines yourself. Set html=true only for a body that is already HTML.

`attachments` are paths on the machine running this server. Each is
attached under its own file name, with the MIME type guessed from that
name and `application/octet-stream` as the fallback.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
ccNo
toYes
bccNo
bodyYes
htmlNo
accountYes
subjectYes
thread_idNo
attachmentsNo
quote_historyNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.10.1
    • addedInput schema / properties / attachments
      Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Attachments"
+}
    • addedInput schema / properties / quote_history
      Added value: +{
+  "default": true,
+  "title": "Quote History",
+  "type": "boolean"
+}
  2. First observedv0.3.0

TDQS

A4.7/5.0
Behavior5/5

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

With no annotations, the description carries the full transparency burden and does so thoroughly. It discloses server-side reply quoting, derived In-Reply-To/References headers, multipart/alternative HTML generation, attachment path semantics, and MIME type guessing—all non-obvious behaviors beyond the basic 'create draft' action.

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 long but justified for a 10-parameter tool with many behavioral quirks. Every sentence carries real guidance: body formatting, reply quoting, HTML mode, attachment handling. It is organized into clear paragraphs and front-loads the core purpose and return value.

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?

For a complex tool with no output schema and no annotations, the description is remarkably complete. It covers the return object, subtle reply behavior, body formatting rules, attachment constraints, and HTML option. The only notable gap is the phantom in_reply_to_message_id reference, but overall the agent has enough context to use 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 description coverage is 0%, so the description must compensate. It does a strong job for body, html, thread_id, quote_history, and attachments, explaining formats and special behavior. However, it references in_reply_to_message_id, which is not present in the input schema, and it does not explain the clear-by-name to/cc/bcc/subject parameters.

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 the tool's purpose with a specific verb and resource: 'Create a Gmail draft.' It also specifies the return shape ({id, message: {...}}), which distinguishes draft creation from sending or updating drafts.

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 reply scenario is explicitly addressed: 'Replies: pass thread_id and nothing else,' and there is clear guidance on when to set html=true. However, it does not explicitly contrast this tool with siblings like gmail_draft_send or gmail_send, leaving some selection inference to the agent.

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

Deploy Server

Other Tools