Skip to main content
Glama
mail-mcp-server

mail-mcp-server

mailbox_overview

Retrieve exact message and unread counts for inbox, tabs, spam, trash, and labels without opening or reading any messages.

Instructions

Exact message and unread counts for the inbox, each tab (primary, promotions, social, updates, forums), spam, trash and every user label. Cheap: no message is read.

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": {
      "mailbox": "<mailbox>"
    },
    "name": "mailbox_overview"
  }
}

Input Schema

NameRequiredDescriptionDefault
mailboxYesA connected mailbox address (see list_mailboxes)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations, the description must carry the behavioral burden; it does disclose the cost profile (no message bodies read) and implicitly that the operation is a read. It says nothing about permissions, whether disconnected mailboxes error, or how large label sets are returned. The cost disclosure is genuinely useful context that annotations would otherwise have to supply.

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: the first enumerates the returned scope, the second preempts the obvious concern about cost. No filler and the scope detail is front-loaded.

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?

This is a simple one-parameter read tool with no output schema, and the description does describe the shape of the return value (counts per tab, folder, and label). What is missing is minor — error behavior for an unknown mailbox and whether counts are exact versus eventually consistent, the latter being implied by "Exact".

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 mailbox parameter is fully documented in the schema, including a pointer to list_mailboxes, so the baseline is a 3. The description itself adds nothing about the parameter — not whether it accepts an alias or address form, nor what happens for an unconnected mailbox.

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?

The description names the exact resource and granularity of what is returned: message and unread counts broken out per inbox tab, spam, trash, and user label. That is specific enough to separate it from search, get_message, and get_thread, which retrieve content rather than counts. It does not explicitly distinguish itself from sender_stats, which is the nearest count-oriented sibling.

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?

"Cheap: no message is read" implies the right usage context — reach for this when only totals are needed instead of reading messages — but the implication is never stated as an instruction. No alternative is named, so an agent must infer that sender_stats or search serve different needs.

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