Skip to main content
Glama

internet

Destructive

Manage WAN connectivity on TP-Link routers: check status, configure IPv4/IPv6 protocols, renew or release leases, enable IPv6, set DNS privacy, clone MAC addresses, and control flow.

Instructions

Internet (WAN). action=status (connection, IPv4/IPv6, WAN port, dual-NAT, speed, DNS privacy) | protocols | get (family=4|6, proto?) | set (family, proto=dynamic|staticip|pppoe|l2tp|pptp|dslite|v6plus|ocn for IPv4; dynamic|static|pppoe|pass|tunnel for IPv6, settings={...}) CRITICAL | renew | release (family) | ipv6_enable | ipv6_disable | autodetect | dns_privacy (settings={dns_privacy: none|doh|dot, dns_mode: default|strict, server_list: [...]}) | dns_privacy_servers (kind=doh|dot) | dns_privacy_test (settings) | mac_clone (settings={mac_clone_type, mac_custom}) | flow_control (settings={rx_enable, tx_enable}).

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": "internet"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNo
applyNofalse (default) = dry run: show the plan, diff, warnings and risk, send nothing. true = send it.
protoNo
actionNostatus
familyNo
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

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=true, idempotentHint=false and openWorldHint=false, so the danger profile is supplied structurally. The description's contribution is flagging which action ('set ... CRITICAL') is the risky one, which is genuinely useful routing signal. It adds nothing about what state is lost on release/renew, permission requirements, or whether changes are revertible via router_undo.

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

Conciseness3/5

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

Extremely token-efficient — one sentence, pipe-delimited, leading with the most common action (status). But the nested parentheses and the dropped-in 'CRITICAL' make it a wall of text that is slow to parse and ambiguous in emphasis. Compactness is achieved at some cost to readability.

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 15-action, 9-parameter destructive tool with no output schema, the description covers every action and most of the settings shapes, which is the core need. It omits the dry-run/apply/confirm_token safety flow and any indication of what status returns, so an agent still has gaps before calling a mutation.

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?

Schema coverage is only 56%, and the description compensates substantially: it gives the proto vocabulary per family (dynamic|staticip|pppoe|l2tp|pptp|dslite|v6plus|ocn vs dynamic|static|pppoe|pass|tunnel), names the settings keys for dns_privacy, mac_clone, and flow_control, and binds kind to the dns_privacy_servers action. The schema only types proto as a bare string, so this is real added meaning. It still leaves settings='{...}' underspecified for the set action.

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?

Opens with the resource ('Internet (WAN)') and then enumerates every action with its sub-scope — status, protocols, get, set, renew, release, ipv6_enable/disable, autodetect, dns_privacy, mac_clone, flow_control. An agent can tell this covers WAN configuration as opposed to LAN, Wi-Fi, or port forwarding. It stops short of an explicit statement of what the tool is for vs siblings, but the verb+resource coverage is specific.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance and no pointers to alternatives (e.g. lan, routing, router_catalog) despite many nearby siblings. The one piece of routing advice, the 'CRITICAL' tag on set, is unlabeled — it does not say what makes it critical or that a dry run and confirm_token precede it. The agent must infer the apply/confirm workflow entirely from the schema.

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