Skip to main content
Glama
@marlinjai/email-mcp

@marlinjai/email-mcp

by marlinjai

email_draft_create

Create a new email draft with recipients, subject, body, and attachments; optionally save it as a reply in an existing message thread.

Instructions

Create a new email draft. Pass inReplyToEmailId to save it as a reply in that message's thread

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": {
      "accountId": "<accountId>",
      "to": "<to>",
      "subject": "<subject>",
      "body": "<body>"
    },
    "name": "email_draft_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
toYes
bodyYes
subjectYes
accountIdYes
signatureNoAdd the account's signature (default true). Gmail: the signature of the send-as address the mail goes out from, read from Gmail's settings, in Gmail's own markup above any quoted history; a body that already holds one is left alone. Outlook.com, iCloud and IMAP have no signature a client can read, so nothing is added there. The result's `signature` field says what happened
attachmentsNoFiles to attach, at most 100. Total size is capped at 25 MB
inReplyToEmailIdNoId of the email this draft replies to. The draft joins that thread (Gmail threadId, Outlook createReply, In-Reply-To/References headers elsewhere)
inReplyToSourceFolderNoFolder of the email named in inReplyToEmailId (required for IMAP/iCloud when that email is not in INBOX). The draft itself is saved to Drafts

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.11.0

TDQS

B3.1/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full behavioral burden. It correctly conveys the non-destructive nature (a draft is saved, not sent) and the reply-threading semantics, but says nothing about signature defaulting, attachment size limits, or where drafts land — those details appear only inside the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with the core action first and the optional threading behavior second; no filler. It is efficient, though extremely sparse given the tool's surface area.

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?

With 8 parameters, nested attachment objects, no annotations, and no output schema, the definition should explain more about required fields and side effects. The description covers only the reply-threading option, leaving an agent to infer the rest from the schema alone.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 50% and four required parameters (accountId, to, subject, body) are undocumented in the schema, yet the description addresses only inReplyToEmailId — which the schema already explains in more detail. It therefore does not compensate for the coverage gap.

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 gives a specific verb and resource ('Create a new email draft') and adds a second capability (reply-thread drafts), which separates it from email_reply and email_draft_update well enough. It does not explicitly name or contrast with those siblings, so it stops short of a 5.

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

Usage Guidelines3/5

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

It gives one concrete routing cue: pass inReplyToEmailId to make the draft a threaded reply. There is no guidance on when to draft versus send (email_reply), when to use email_draft_update instead, or any prerequisite about account selection.

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