Skip to main content
Glama
Sign In
gmail-mcp

gmail-mcp

by DimitrisPasakaleris
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

create_draft

Save an email as a draft in Gmail without sending it, so you can review or edit it before manual sending. Requires to, subject, and body; supports cc, bcc, and attachments.

Instructions

Create a draft email saved in Gmail's Drafts folder — not sent immediately.
Review it in Gmail before sending manually.

Required:
  to (str) — recipient email address.
  subject (str) — email subject line.
  body (str) — email body text.

Optional:
  cc (str, default="") — CC recipients.
  bcc (str, default="") — BCC recipients.
  attachments (list[str] | None, default=None) — file paths to attach.

Returns on success:
  {"draft_id": "...", "message_id": "..."}

Workflow note: Drafts are saved to Gmail, not stored locally.
  Use list_drafts() to see all drafts. Use update_draft(draft_id, ...)
  to modify a draft. Use delete_draft(draft_id) to remove.
  The draft stays in Gmail until manually sent or deleted.

Input Schema

NameRequiredDescriptionDefault
ccNo
toYes
bccNo
bodyYes
subjectYes
attachmentsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does well: it discloses that nothing is sent, the draft lives server-side in Gmail rather than locally, and it persists until manually sent or deleted. It omits auth/permission requirements and failure modes, keeping it short of a 5.

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?

Front-loaded with the core purpose, then cleanly blocked into Required, Optional, Returns, and Workflow. Every block adds information an agent needs, and nothing is repeated from the schema verbatim beyond the field names themselves.

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 6-parameter mutation tool with no annotations and no output schema, the description covers the mutation consequence, all parameters, the success return shape, and the surrounding draft lifecycle with named sibling tools. Nothing material is missing.

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, and it does: it groups required (to/subject/body) vs optional (cc/bcc/attachments), states defaults, and clarifies that attachments are file paths. It could add format hints (e.g., multiple addresses in cc/bcc), which holds it at 4.

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?

States a specific verb+resource ('Create a draft email saved in Gmail's Drafts folder') and immediately distinguishes itself from the send path with 'not sent immediately.' An agent can tell this apart from send_email/reply_email without inspecting either schema.

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 workflow note gives concrete routing: use list_drafts to see drafts, update_draft to modify, delete_draft to remove, and notes the draft persists until manually sent or deleted. The only gap is it never explicitly contrasts with send_email for the 'send now' case, though 'not sent immediately' implies it.

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