Skip to main content
Glama

qq_watchdog

Read-only

Check the login watchdog that keeps QQ signed in through automatic re-login, pop-up dismissal, and client restarts. Run an immediate check and get notified when a QR scan is required.

Instructions

State of the login watchdog that keeps QQ logged in automatically (re-clicks 登录 for the remembered account, dismisses 下线 pop-ups, restarts a stuck client, notifies when a QR scan is really needed). check_now=true runs a check immediately.

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": "qq_watchdog"
  }
}

Input Schema

NameRequiredDescriptionDefault
check_nowNoRun one check now

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.3/5.0
Behavior2/5

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

The description is genuinely informative about behavior the annotations do not convey: the watchdog re-clicks login, dismisses 下线 pop-ups, restarts a stuck client, and notifies only when a real QR scan is needed. However, those disclosed actions are side-effecting (clicks, process restarts), which sits uneasily with readOnlyHint=true and destructiveHint=false — an agent reading the structured hints could wrongly assume calling with check_now=true is a pure read. The description also never says whether restarts happen only under check_now or continuously in the background.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded in the first clause, and the dense parenthetical efficiently packs in four distinct watchdog behaviors; the check_now sentence is cleanly separated. It is slightly overpacked — the parenthetical mixes what the watchdog does with what this tool reports — but no sentence is wasted.

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 single-boolean tool with no output schema, the description is close to sufficient: it explains the monitored domain and the one parameter's effect. The main gap is that it never indicates what the returned "state" contains or whether triggering a check can change that state, leaving the agent to infer the response 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?

There is only one optional boolean and schema coverage is 100% ("Run one check now"), so the schema already carries the parameter. The description restates it as "check_now=true runs a check immediately," adding the implication of trigger semantics but no detail on what the triggered check does or returns, so it does not meaningfully exceed the schema 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?

The description gives a specific noun+role ("state of the login watchdog") and then enumerates concrete behaviors it owns: re-clicking 登录 for the remembered account, dismissing 下线 pop-ups, restarting a stuck client, and QR-scan notification. That makes the tool's scope readable without opening the schema, though it never distinguishes this from siblings such as qq_login_status or qq_restart_client, which cover overlapping territory.

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: "check_now=true runs a check immediately" hints that the default call is a passive state read and that check_now forces action. There is no explicit when-to-use/when-not guidance and no pointer to qq_login_status or qq_restart_client for agents who want a plain status check or a manual restart.

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

Deploy Server

Other Tools