Skip to main content
Glama

system

Destructive

Manage TP-Link router configuration: check firmware, read or change DDNS, device priority, LED, eco, time, QoS, and firewall, sync time, or reboot with dry-run safeguards.

Instructions

System settings. action=info (all of the below) | firmware_check (ask TP-Link for updates; changes nothing) | ddns (read) | device_priority (list) | set_device_priority (mac, enable, time_period) | led / led_night / eco / time / dst / hour24 / auto_upgrade / qos / firewall (no settings = read; settings={...} or enable=bool = change) | time_sync | reboot (CRITICAL, not undoable).

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": "system"
  }
}

Input Schema

NameRequiredDescriptionDefault
macNo
applyNofalse (default) = dry run: show the plan, diff, warnings and risk, send nothing. true = send it.
actionNoinfo
enableNo
revealNoShow secrets (passwords/keys) unmasked.
routerNoWhich router (see router_status 'routers'); default main.main
settingsNo
time_periodNo
confirm_tokenNoRequired with apply=true for CRITICAL changes: the token from the dry run (valid 5 minutes, bound to the exact plan and current router state).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A3.5/5.0
Behavior3/5

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

The annotations already declare destructiveHint=true, readOnlyHint=false and non-idempotent, and the description adds real context on top: which actions are pure reads, that firmware_check changes nothing, and that reboot is irreversible. It omits the dry-run/apply/confirm_token safety workflow (only present in the schema), so the operational picture beyond annotations is only partly filled in.

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 pipe-delimited action map is dense and front-loaded with the purpose, and nearly every token conveys an action or a mode rule. Minor cost: 'all of the below' is slightly ambiguous and the run-together form is harder to scan than a short list.

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

Completeness3/5

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

For a 16-action multiplexer with a destructive reboot and a dry-run/confirm-token protocol, the description covers action semantics but not the apply/confirm workflow, return shapes, or overlap with the sibling ddns tool. With no output schema, an agent still lacks guidance on what info returns.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

At 44% schema coverage the description must carry weight, and it does: it defines the action semantics, maps mac/enable/time_period to set_device_priority, and explains that settings={...} or enable=bool triggers a change. apply, confirm_token, reveal and router remain undocumented in the description, though the schema describes those four well.

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 enumerates every accepted action value and states what each does (firmware_check 'ask TP-Link for updates; changes nothing', device_priority 'list', reboot 'CRITICAL, not undoable'), so an agent can tell the sub-operations apart. The overall framing 'System settings' is broad for a 16-action dispatcher, but the per-action list compensates.

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?

It gives a useful rule for the read/write split ('no settings = read; settings={...} or enable=bool = change') and flags reboot as CRITICAL. However it never routes the agent to alternatives, notably the sibling 'ddns' tool, which appears to overlap with action=ddns here, and it says nothing about when to use this versus router_status or the dedicated set_* tools.

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