Skip to main content
Glama

lan

Destructive

Configure and inspect the router's local network: IP/mask, port speed, link aggregation, flow control, IPTV VLANs, NAT and ALG, with dry runs and confirm tokens for critical changes.

Instructions

LAN side. action=status (all below + port status) | lan_ipv4 (router LAN IP/mask: CRITICAL) | lan_ipv6 | port_speed (settings={speed}) | link_aggregation (LACP: enable_agg, hashmode, lacpmode, port_settings) | flow_control (rx_enable, tx_enable) | iptv (IPTV/VLAN: enable, mode, internet/iptv/ipphone VLAN ids, IGMP, port_settings) | udp_proxy | nat (NAT and hardware NAT boost) | alg (settings={ftp, tftp, h323, rtsp, sip, pptp, l2tp, ipsec: true/false}). Firewall / ping replies: system action=firewall. No settings = read.

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": "lan"
  }
}

Input Schema

NameRequiredDescriptionDefault
applyNofalse (default) = dry run: show the plan, diff, warnings and risk, send nothing. true = send it.
actionNostatus
enableNo
revealNoShow secrets (passwords/keys) unmasked.
routerNoWhich router (see router_status 'routers'); default main.main
settingsNofields to change (see the matching router_catalog form)
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

A3.8/5.0
Behavior4/5

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

Annotations already flag this as destructive and non-idempotent, but the description adds genuinely new behavior: it marks lan_ipv4 as CRITICAL (which explains why confirm_token exists in the schema) and establishes that omitting settings makes the call a read. That CRITICAL designation is the key risk signal an agent needs before attempting a write. It still does not describe what state is destroyed or what a plan/diff response looks like, keeping it below a 5.

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 list packs ten actions plus their key fields into a few dense lines with no filler, and the read-behavior note is placed at the end as a closing rule. Density hurts scannability slightly, but every clause carries information an agent would otherwise have to discover from the schema.

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 ten-action destructive tool with a nested settings object and no output schema, the definition covers action selection, which action is CRITICAL, the read-only path, and the firewall handoff to system. The remaining gaps — how to obtain a confirm_token beyond the schema text, and what the dry-run plan contains — are already documented in the input schema, so the description is fit for purpose.

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?

With 71% schema coverage the baseline is already high, yet the description compensates for the undescribed action and settings parameters by spelling out the per-action settings payloads: {speed} for port_speed, enable_agg/hashmode/lacpmode/port_settings for LACP, rx_enable/tx_enable for flow control, and VLAN ids plus IGMP for IPTV. That is real meaning beyond the schema, though 'settings' still ultimately defers to router_catalog rather than documenting all fields.

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 opens with 'LAN side' and enumerates the concrete resources it manages (LAN IPv4/IPv6, port speed, LACP, flow control, IPTV/VLAN, UDP proxy, NAT/ALG), so an agent can tell it configures LAN-side router settings rather than WAN or wireless. The action menu effectively acts as a compact verb list. It loses a point only because the tool name 'lan' alone carries no verb and the framing is a menu rather than a single stated purpose.

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 one explicit routing rule — 'Firewall / ping replies: system action=firewall' — and states 'No settings = read', which tells the agent how to switch between reading and writing. However, it never says when to prefer this tool over other LAN-adjacent siblings such as routing, dhcp_server_set, or wifi_set, so the choice among alternatives is left to inference.

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