Skip to main content
Glama

Email: Create draft

email_create_draft

Create an email draft without sending. If replying, first read the source email and use the provider-appropriate reply_to_message_id (IMAP may use RFC822 Message-ID).

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": {
      "to": "<to>"
    },
    "name": "email_create_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
ccNo
toYes
bccNo
htmlNo
subjectNo
account_idNoOptional Nilyo connection ID (unipile_account_id from list_connected_accounts). Omit when the user has one account for this provider. When several exist, Nilyo never guesses: list them (display name, identifier, provider user ID), choose the one the user named or ask, and pass its ID here.
plain_textNo
reply_to_message_idNoReply reference. Gmail/Outlook normally use provider email ID; IMAP may require RFC822 Message-ID from the read email. Email reply reference: For Gmail/Outlook normally use the provider email id. For generic IMAP, reply_to_message_id may be the RFC822 Message-ID returned in the email data. Obtain with: email_read_message -> inspect id and provider/RFC Message-ID fields Never pass: subject, sender email address.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / bcc / items / properties / email / pattern
      Previous value: -"^(?!\\.)(?!.*\\.\\.)([A-Za-z0-9_'+\\-\\.]*)[A-Za-z0-9_+-]@([A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"New value: +"^(?:[A-Za-z0-9_'+\\-]+\\.)*[A-Za-z0-9_'+\\-]*[A-Za-z0-9_+-]@(?:[A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"
    • changedInput schema / properties / cc / items / properties / email / pattern
      Previous value: -"^(?!\\.)(?!.*\\.\\.)([A-Za-z0-9_'+\\-\\.]*)[A-Za-z0-9_+-]@([A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"New value: +"^(?:[A-Za-z0-9_'+\\-]+\\.)*[A-Za-z0-9_'+\\-]*[A-Za-z0-9_+-]@(?:[A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"
    • changedInput schema / properties / to / items / properties / email / pattern
      Previous value: -"^(?!\\.)(?!.*\\.\\.)([A-Za-z0-9_'+\\-\\.]*)[A-Za-z0-9_+-]@([A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"New value: +"^(?:[A-Za-z0-9_'+\\-]+\\.)*[A-Za-z0-9_'+\\-]*[A-Za-z0-9_+-]@(?:[A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"
  2. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare a non-read-only but non-destructive write with a closed-world scope, and the description reinforces that no message leaves the account ("without sending") plus a prerequisite step of reading the source email before replying. It doesn't disclose where the draft lands (Drafts folder), whether duplicates are created, or what ID comes back, which keeps it from 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?

Two sentences, both front-loaded and free of filler, with the reply prerequisite placed immediately after the core action. Nothing would be lost by keeping it exactly as is.

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

Completeness3/5

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

For an 8-parameter write tool with no output schema, the description covers purpose and the reply path but omits how html and plain_text relate, whether subject is required in practice, and what the caller receives back (a draft ID for later email_send_draft). Those gaps matter for chaining into downstream draft tools.

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 coverage is only 25%, so the description must carry weight; it does add real cross-tool meaning for reply_to_message_id by tying its value to email_read_message and noting the IMAP RFC822 Message-ID variant. The remaining parameters (subject, html vs plain_text, cc/bcc) get no clarification beyond their bare schema types, leaving the coverage gap largely unaddressed.

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 opens with a concrete verb+resource, "Create an email draft," and immediately scopes it with "without sending," which cleanly separates it from email_send and email_send_draft. It stops short of distinguishing it from the other draft siblings (email_update_draft, email_get_draft), but the core intent is unambiguous.

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 a conditional workflow for one case: "If replying, first read the source email and use the provider-appropriate reply_to_message_id." Nothing is said about when to use email_create_draft versus email_update_draft or when to escalate to email_send_draft after drafting, so the alternative-selection guidance is only partial.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.