Skip to main content
Glama

create-reply-draft

Destructive

Creates a draft reply to an email message, supporting JSON or MIME format, and preserving reply-to recipients.

Instructions

Create a draft to reply to the sender of a message in either JSON or MIME format. When using JSON format:

  • Specify either a comment or the body property of the message parameter. Specifying both will return an HTTP 400 Bad Request error.

  • If replyTo is specified in the original message, per Internet Message Format (RFC 2822), you should send the reply to the recipients in replyTo, and not the recipients in from.

  • You can update the draft later to add reply content to the body or change other message properties. When using MIME format:

  • Provide the applicable Internet message headers and the MIME content, all encoded in base64 format in the request body.

  • Add any attachments and S/MIME properties to the MIME content. Send the draft message in a subsequent operation. Alternatively, reply to a message in a single operation.

💡 TIP: For HTML replies pass Message.body.contentType: 'html' with Message.body.content as HTML. Note: supplying Message.body replaces the whole draft body, so the original quoted history is not included. Specifying both 'comment' and Message.body returns 400. Signatures are added by the Outlook client only, not via Graph.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bodyYes
messageIdYesPath parameter: messageId
includeHeadersNoInclude response headers (including ETag) in the response metadata
excludeResponseNoExclude the full response body and only return success or failure indication
Behavior1/5

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

Description contradicts annotations: it describes a non-destructive creation, but annotations set destructiveHint: true. The description does not explain this inconsistency or disclose any destructive behavior.

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

Conciseness3/5

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

Description is verbose with several paragraphs and a bullet list. While structured, it could be more concise. The tip with emoji adds some noise.

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?

Covers format options and constraints but does not mention return values (no output schema) or how to send the draft. Complete for the functional behavior but lacks full context.

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?

Adds significant meaning beyond the schema by explaining constraints (comment vs body, replyTo rules) and format instructions. Schema coverage is 75%, and the description fills gaps with usage tips.

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?

The description clearly states it creates a draft to reply to the sender, with specific formatting options (JSON/MIME). It distinguishes from sibling tools like create-forward-draft and create-reply-all-draft by specifying 'reply to the sender'.

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?

Provides guidance on using JSON vs MIME format, including constraints (comment vs body, replyTo behavior). However, it does not explicitly contrast with sibling tools (e.g., when to use create-reply-draft vs reply-mail-message).

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Softeria/ms-365-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server