Skip to main content
Glama

create_draft

Draft Gmail messages without sending them; include recipients, replies, and attachments, then review before explicit user confirmation to send.

Instructions

Prepare a Gmail draft without sending it (sending: send_draft, only after the user's yes).

As a reply (replyToMessageId, or threadId to answer the last message of the thread): In-Reply-To, References, "Re:" subject and Gmail thread are filled in; to then defaults to the sender (or Reply-To). Attachments: absolute paths of local files, 25 MB in total; never from a secrets location (vaults, SSH keys, tokens): refused.

Args: body: plain text body (no Markdown). to: recipients (list of addresses, or "Name a@example.com, b@example.com"); required unless replying. subject: subject; when replying and empty, the original subject with "Re:". cc: carbon copy, optional. bcc: blind carbon copy, optional. replyToMessageId: ID of the Gmail message to reply to. threadId: thread to reply to (its last message) when replyToMessageId is empty. attachments: absolute paths of the files to attach, optional.

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": {
      "body": "<body>"
    },
    "name": "create_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
ccNo
toNo
bccNo
bodyYes
subjectNo
threadIdNo
attachmentsNo
replyToMessageIdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.12.3
    • changedOutput schema / (root)
      Previous value: -{
      -  "properties": {
      -    "result": {
      -      "title": "Result",
      -      "type": "string"
      -    }
      -  },
      -  "required": [
      -    "result"
      -  ],
      -  "title": "create_draftOutput",
      -  "type": "object"
      -}New value: +null
  2. First observedv0.1.0

TDQS

A4.7/5.0
Behavior4/5

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

Adds substantial behavior beyond the annotations: reply mode auto-fills In-Reply-To, References, a "Re:" subject and the Gmail thread, and `to` defaults to the sender/Reply-To. It also discloses two hard limits an agent could otherwise trip over — 25 MB total attachments from absolute local paths, and an outright refusal for secrets locations (vaults, SSH keys, tokens). Missing only whether the draft response includes an ID or how it interacts with existing drafts.

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?

Front-loaded with the core action and the send_draft hand-off, then a reply-mode paragraph, then an Args list. Nearly every sentence earns its place, though the reply paragraph is dense and the Args list is somewhat cramped for an agent parsing it in one pass.

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?

Eight parameters with zero schema descriptions are all covered, the draft-vs-send boundary is explicit, and reply construction and attachment limits are spelled out. No output schema exists, but the description's job of enabling a correct call is fully met.

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

Parameters5/5

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

Schema coverage is 0%, so the description carries the full burden and does: all eight parameters are explained, including the accepted address syntax (list or "Name <a@example.com>, b@example.com"), the plain-text-only body rule, the required-unless-replying condition on `to`, and the replyId-wins-over-threadId precedence.

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 and resource ("Prepare a Gmail draft") and immediately bounds the scope with the negative constraint "without sending it," pointing at the sibling send_draft. An agent can distinguish this from update_draft, send_draft, or get_draft without opening any schema.

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

Usage Guidelines5/5

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

Explicitly routes the send path to send_draft and gates it on user confirmation ("only after the user's yes"). Also names the two reply entry points (replyToMessageId vs threadId when the former is empty), so the agent knows which parameter selects which mode.

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