Skip to main content
Glama
nabheet

google-services-mcp

by nabheet
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Create email draft

google_gmail_drafts_create

Create a draft email in Gmail without sending it, allowing you to prepare and review messages before dispatch.

Instructions

Create a draft email (not sent).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
ccNoCC recipient(s).
toYesRecipient email(s).
bccNoBCC recipient(s).
bodyYesMessage body.
fromNoSend-as alias or address to set as the From header.
accountNoAccount nickname to use.
replyToNoAddress to set as the Reply-To header.
subjectYesSubject line.
bodyTypeNoBody format (default text).
attachmentsNoLocal files to attach to the draft.
driveFileIdsNoDrive file IDs to attach by reference (downloaded under the Gmail size limit).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv0.1.60
    • addedInput schema / properties / attachments / items / properties / cid
      Added value: +{
+  "description": "Content-ID for inline parts so HTML can reference them as cid:<cid>.",
+  "type": "string"
+}
    • addedInput schema / properties / attachments / items / properties / disposition
      Added value: +{
+  "description": "How the part is presented (default attachment; inline embeds it in the body).",
+  "enum": [
+    "attachment",
+    "inline"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / driveFileIds
      Added value: +{
+  "description": "Drive file IDs to attach by reference (downloaded under the Gmail size limit).",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
    • addedInput schema / properties / from
      Added value: +{
+  "description": "Send-as alias or address to set as the From header.",
+  "type": "string"
+}
    • addedInput schema / properties / replyTo
      Added value: +{
+  "description": "Address to set as the Reply-To header.",
+  "type": "string"
+}
  2. Addedv0.1.30

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states only that the email is not sent; it does not cover authentication requirements, which account is used, whether the draft is saved persistently, or what happens to unspecified fields.

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 a single front-loaded sentence with no redundant or wasted text. It communicates the core action and the key non-sending behavior directly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has 11 parameters, no annotations, and no output schema. A single sentence is too sparse for this complexity; an agent would lack context about draft persistence, account selection, or how the created draft is identified for later use.

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 11 parameters are already documented in the input schema. The description adds no parameter-level meaning beyond what the schema provides, making the baseline score of 3 appropriate.

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 description states a specific verb and resource: creating an email draft, and clarifies it is not sent. This distinguishes it from send operations, though it does not name the sibling tools such as google_gmail_send or google_gmail_drafts_send.

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

Usage Guidelines2/5

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

The description offers no guidance on when to use this tool versus alternatives. The parenthetical '(not sent)' is a behavioral note, not an explicit when-to-use or when-not-to-use rule, and no alternative tools are named.

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