Skip to main content
Glama
gmail-mcp
by gchallen

get_thread

Read-only

Reads a Gmail thread's complete conversation, returning every message oldest first with bodies and marking drafts with the DRAFT label.

Instructions

Read a whole conversation: every message in the thread, oldest first, with bodies. Drafts in the thread are included as messages with the DRAFT label.

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": {
      "threadId": "<threadId>"
    },
    "name": "get_thread"
  }
}

Input Schema

NameRequiredDescriptionDefault
formatNoWhich fields to return. "plain_text" (default): headers, snippet, labels, attachments list and the text body (HTML converted to text when there is no text part). "full": plain_text plus htmlBody. "minimal": headers, snippet and labels only, no body. "metadata": like minimal but without subject or snippet. "raw": the RFC 822 source.
threadIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2026.9.2

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, non-destructive, openWorld), and the description goes further by disclosing result ordering (oldest first) and the non-obvious inclusion of drafts labeled DRAFT. It doesn't discuss size limits or truncation on very long threads, 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 load-bearing, with the scope and ordering front-loaded and the draft caveat following. No redundant restatement of the tool name or boilerplate.

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

Completeness4/5

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

With no output schema, the description does the work of saying what comes back (messages with bodies, ordering) and behavioral quirks (drafts as DRAFT-labeled messages). Return-field selection is delegated to the format enum, which is sufficient; only edge cases like thread size limits are unaddressed.

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%: the 'format' enum is thoroughly self-documented in the schema (including its default), while 'threadId' is undocumented but self-evident. The description adds no parameter meaning beyond the schema, so this sits at the baseline.

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 ('Read a whole conversation: every message in the thread') with the ordering made explicit ('oldest first'). The emphasis on 'whole conversation' implicitly contrasts it with a single-message reader, but no sibling is named, so differentiation is left to inference.

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?

The use case (reading an entire thread) is implied by the description's scope statement, but there is no explicit when/when-not guidance and no reference to alternatives such as get_message for one message or search_threads for locating a threadId. Adequate but leaves routing to the agent.

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