Skip to main content
Glama
Google Workspace MCP connector

Google Workspace MCP connector

by animesh-ex

gmail_search

Read-only

Search Gmail with query syntax to locate emails by sender, subject, attachment, or read status, returning message headers and snippets.

Instructions

Search Gmail using Gmail query syntax (e.g. 'from:alice is:unread newer_than:7d', 'has:attachment subject:invoice'). Returns message headers and snippets.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "gmail_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryNoGmail search queryin:inbox
pageTokenNo
maxResultsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.1

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds that results are headers and snippets only (not full bodies), which is genuinely useful context, but it says nothing about pagination, result caps, or how many messages a broad query could surface in an open-world mailbox.

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: the operation and its query dialect come first, the return shape last. The inline examples earn their space by demonstrating the required syntax rather than padding the text.

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 a three-parameter, zero-required search tool with no output schema, the description covers the query dialect and return shape adequately. It omits pagination behavior and the existence of a result cap, leaving an agent to discover via the schema that results are paged and bounded at 100.

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?

With only 33% schema description coverage, the description compensates for the query parameter by naming Gmail search syntax and giving two concrete operator examples, which is more than the schema's bare "Gmail search query". However, pageToken and maxResults are left entirely undocumented in both places, so the coverage gap is only partly closed.

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?

States a specific verb and resource ("Search Gmail") plus what comes back ("message headers and snippets"), which implies a read-only list-style operation distinct from the read_message/read_thread siblings. It never names an alternative explicitly, so differentiation is inferred rather than stated.

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?

Usage is only implied: the examples of query syntax show how to narrow a search but not when to choose this tool over gmail_read_message, gmail_read_thread, or gmail_list_drafts. There are no stated exclusions, prerequisites, or triggers for switching tools.

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