Skip to main content
Glama
Google Workspace MCP connector

Google Workspace MCP connector

by animesh-ex

gmail_reply

Reply or reply-all to an existing email while keeping it in the same thread, with options to attach files and send immediately or save as a draft.

Instructions

Reply (or reply-all) to an existing email, keeping it in the same thread. Supports attachments.

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": {
      "messageId": "<messageId>",
      "body": "<body>"
    },
    "name": "gmail_reply"
  }
}

Input Schema

NameRequiredDescriptionDefault
ccNoExtra cc recipients
bodyYes
htmlNo
sendNowNofalse = save as draft instead of sending
replyAllNo
messageIdYesID of the message being replied to
driveFileIdsNoDrive file IDs/URLs to attach. Google Docs/Slides are attached as PDF, Sheets as XLSX.
attachmentPathsNoAbsolute local file paths to attach

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.1

TDQS

A3.7/5.0
Behavior3/5

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

Annotations already declare this is a non-read-only, open-world, non-destructive operation. The description adds thread preservation and attachment support, but does not disclose that it sends immediately by default or that sendNow=false saves a draft, nor does it add permission or rate-limit context.

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 tight sentences front-load the core action and thread behavior with no filler. It is appropriately sized for a short tool description, though the content is sparse relative to the tool's complexity.

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 mutation with no output schema, the description gives the core action and attachment capability, while annotations cover the safety profile. It remains thin on the consequential send-versus-draft behavior and optional parameter semantics, relying heavily on the schema.

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 63%: messageId, cc, sendNow, driveFileIds, and attachmentPaths have descriptions, while body, html, and replyAll do not. The description maps to replyAll and the attachment parameters, but adds no clarification for body, html, cc, or sendNow semantics.

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 the specific verb 'Reply' (and reply-all) on an existing email, plus thread retention and attachment support. That clearly separates it from gmail_send and draft-creation siblings by requiring an existing message and preserving the thread.

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?

Implies use when responding to an existing email in the same thread, but never explicitly says when to choose it over gmail_send, gmail_create_draft, or gmail_send_draft, nor when not to use it. The context is clear enough, but guidance is only implied.

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