Skip to main content
Glama

device_log

Read-onlyIdempotent

Get everything a TP-Link router knows about one device by MAC—online state, IP, DHCP lease, router-log lines, blocked sites, parental-control and traffic status—plus record changes to a local history and query it.

Instructions

Everything the router knows about ONE device, plus a local per-MAC history. action=report (mac: online state, IP, DHCP lease/reservation, every router-log line mentioning its MAC or IP, its parental-control profile's sites today and blocked attempts, access-control / VPN / IoT status, traffic) | record (mac: append only what is NEW to /device-logs/-.jsonl; run it on a timer for a continuous log beyond what the router keeps) | history (mac, event?, limit) | list. Read-only on the router.

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": "device_log"
  }
}

Input Schema

NameRequiredDescriptionDefault
macNo
eventNo
limitNo
actionNoreport
revealNoShow secrets (passwords/keys) unmasked.
routerNoWhich router (see router_status 'routers'); default main.main

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A3.5/5.0
Behavior1/5

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

The description explicitly says the record action appends new data to '<state>/device-logs/<router>-<MAC>.jsonl' and is meant to run on a timer. That is a persistent local write, while the annotations declare readOnlyHint=true and destructiveHint=false. The phrase 'Read-only on the router' narrows the scope but does not resolve the contradiction with a read-only tool-level annotation.

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 description is front-loaded and densely informative, with action modes separated by pipes. It is compact but reads as a run-on sentence, and the pipe-heavy format is efficient rather than polished.

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 six-parameter tool with no output schema, it explains the returned device data and the local history mechanism well. It still leaves 'list' unexplained and does not clarify limit behavior, but the core action semantics and persistence model are covered.

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?

With schema description coverage at 33%, the description does useful work by explaining the action enum values and tying mac to each mode. However, it leaves limit and event semantics mostly to the schema, and reveal/router rely on their schema descriptions rather than added prose.

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 states a specific resource and scope: 'Everything the router knows about ONE device, plus a local per-MAC history.' It then enumerates the four actions (report, record, history, list) and what report contains, making it easy to distinguish from sibling router-log or device-list tools.

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?

It gives clear per-action usage: report for a full device snapshot, record for appending only new events to a local JSONL log and running on a timer, history for stored events, and list for enumeration. It does not explicitly compare against sibling tools such as router_logs or clients, but the action-mode guidance is strong.

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