Skip to main content
Glama
mail-mcp-server

mail-mcp-server

connect

Links a Gmail mailbox by returning Google's consent URL for browser approval, and restores expired tokens; whichever account consents becomes the mailbox.

Instructions

Connect a Gmail mailbox (or reconnect one whose token expired). Opens Google's consent page in a browser and returns its URL at once; the person consents there, then list_mailboxes shows the result. The mailbox is whichever account they consent with.

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": "connect"
  }
}

Input Schema

NameRequiredDescriptionDefault
login_hintNoOptional address to preselect on the consent page

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

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 does so well: it discloses that a browser consent page is opened, that the call is non-blocking ("returns its URL at once"), that a human must act externally, and how to confirm success. It leaves out scope/permission details and failure behavior, but the interaction model is unusually well conveyed.

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?

Three short sentences, front-loaded with the action, followed by the mechanism and the verification path. Every sentence adds information an agent needs; nothing is redundant.

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, no-annotation, no-output-schema tool, the description covers purpose, return value (the URL), the human-consent step, and how to check the outcome. Only error handling and requested scopes are unaddressed, which are minor gaps here.

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 100% for the single login_hint parameter, so the schema already explains it; the description adds no parameter-specific syntax or fallback detail. It does clarify which mailbox ends up connected (whichever account consents), which is useful semantics adjacent to the parameter, so the baseline 3 holds rather than being penalized.

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?

States a specific verb and resource ("Connect a Gmail mailbox") and adds the alternate case ("reconnect one whose token expired"), so an agent can tell this apart from list_mailboxes or any mail-content sibling. The verb+object+scope is unambiguous.

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?

Gives clear workflow context: the tool returns a consent URL, the person completes consent out-of-band, and list_mailboxes verifies the result. It does not name an explicit alternative or say when not to call it, but the sequencing guidance is enough to select and follow up correctly.

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