Skip to main content
Glama

list_unread

List recently active chats with unread messages or new thread replies, using your last read time to identify what needs review without marking anything as read.

Instructions

List the page_size most recently active chats with messages you haven't read.

A chat counts as unread when it has messages newer than your last_read_time or new replies in a thread you follow. Google gives no count of unread messages. Use read_messages and compare create_time with last_read_time to see what is new. Reading here does not mark anything read.

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": "list_unread"
  }
}

Input Schema

NameRequiredDescriptionDefault
page_sizeNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.0.2

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the full burden, and it discloses meaningful behavior: the unread definition, that results are limited to the most recently active chats, that no server-side unread count exists, and critically that this call has no side effect on read state. It omits auth requirements, rate limits, and ordering guarantees, so it's strong but not exhaustive.

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?

Four short sentences, front-loaded with the action and scope, then the unread definition, then the caveat about counts and the no-mark-as-read guarantee. Every sentence adds information an agent needs to interpret the results correctly.

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?

For a one-parameter list tool with an output schema, the description covers the important semantics: what qualifies as unread, how results are ordered/limited, and that reads are non-mutating. Remaining gaps (pagination beyond page_size, max value, auth) are minor given the output schema handles return shape.

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?

The single parameter has 0% schema description coverage, and the description only ties page_size to selecting the most recently active chats. It doesn't state a maximum, default, or what happens when the cap is hit, so an agent learns the parameter's intent but not its full 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?

The description opens with a specific verb, resource, and scope: 'List the page_size most recently active chats with messages you haven't read.' It then defines precisely what 'unread' means (messages newer than last_read_time, or new replies in a followed thread), which lets an agent distinguish this tool from siblings like read_messages or search_messages without opening a schema.

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?

The description gives clear context for when to use the tool, explains that Google provides no unread count, and routes the agent to read_messages with a create_time vs last_read_time comparison to determine what is actually new. It also warns that reading here does not mark anything read. It doesn't state explicit exclusions (e.g., when to prefer search_messages instead), which keeps it just short of a 5.

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