Skip to main content
Glama
Google Workspace MCP connector

Google Workspace MCP connector

by animesh-ex

gmail_send

Send a new email with cc/bcc recipients, HTML bodies, and attachments from local files or Google Drive.

Instructions

Send a new email. Supports cc/bcc, HTML bodies, and attachments from local files or Google Drive.

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>",
      "subject": "<subject>",
      "body": "<body>"
    },
    "name": "gmail_send"
  }
}

Input Schema

NameRequiredDescriptionDefault
ccNo
toYesComma-separated recipients
bccNo
bodyYes
htmlNoTreat body as HTML
subjectYes
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

B3.3/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=true, so the agent knows this is a non-destructive write that reaches external recipients. The description adds useful capability context (attachment sources, HTML bodies) but says nothing about irreversibility of sending, attachment size limits, or what a successful send returns.

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 short sentences, front-loaded with the core action and followed by capability scope. Nothing is redundant or padded.

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?

With 8 parameters, no output schema, and an open-world send action, the definition is adequate but thin. It omits what happens on success, attachment size limits, and whether the sent message starts or extends a thread – details an agent calling an email-send tool would benefit from.

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 50% – cc, bcc, subject, and body are undocumented in the schema. The description mentions cc/bcc and HTML bodies but adds no format details (e.g., comma-separated cc/bcc, how html interacts with body), so it only marginally compensates 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?

"Send a new email" states a specific verb and resource, and the second sentence enumerates the supported capabilities (cc/bcc, HTML, attachments from local files or Drive). It implicitly distinguishes itself from the draft siblings (gmail_send_draft, gmail_create_draft) by saying "send," though it never names them.

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

Usage Guidelines2/5

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

There is no explicit guidance on when to use this versus gmail_send_draft, gmail_create_draft, or gmail_reply. An agent must infer from the tool name alone that replies belong to gmail_reply and drafts to the draft tools; the description provides no such routing.

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