Skip to main content
Glama

mesh

Destructive

Inspect and control TP-Link Wi-Fi 7/BE router nodes: view status, clients, and topology; enable/disable satellites, link/unlink units, rebalance clients, and apply settings with dry-run safety.

Instructions

EasyMesh: action=status|devices|clients|topology|search_status|ap_avoidance|device_detail (mac) (read) | pair (DISABLED: locked up a BE9300 in testing; use the web UI / Tether / WPS button) | enable | disable (CRITICAL if satellites are attached) | search_start | search_stop | link | unlink (CRITICAL) | reboot_satellite (CRITICAL) | add_onboarding (mac) | set_device (mac, settings={name, location, led, preferred_wifi_uplink_ap, traffic_separation, backhaul_steering}) | rebalance (clients re-pick the best unit) | bind_client (mac=unit, client_mac, bind=true|false: pin a client to a unit). Satellite firmware: maintenance action=firmware_check / satellite_firmware_update.

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": "mesh"
  }
}

Input Schema

NameRequiredDescriptionDefault
macNo
bindNo
waitNopair: seconds to keep WPS open (default 125)
applyNofalse (default) = dry run: show the plan, diff, warnings and risk, send nothing. true = send it.
actionNostatus
revealNoShow secrets (passwords/keys) unmasked.
routerNoWhich router (see router_status 'routers'); default main.main
settingsNo
client_macNo
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).
i_understand_this_locked_up_a_routerNopair is disabled unless this is true

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A3.9/5.0
Behavior5/5

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

With destructiveHint=true already declared, the description still adds substantial context: it marks which actions are read-only, which are CRITICAL (disable, unlink, reboot_satellite), that the entire pair flow is functionally disabled because it locked up a BE9300, and it redirects to non-tool alternatives. That is exactly the kind of operational risk and non-obvious failure context an agent cannot infer from annotations.

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?

There is no filler — every clause conveys risk level, parameter meaning, or a disabled path — but the whole 19-action surface is compressed into one pipe-delimited run-on sentence, making it hard to scan which actions are reads versus destructive writes. Grouping reads and critical writes separately would have preserved the density while improving retrievability.

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 an 11-parameter, destructive, multi-action dispatcher with no output schema, the description covers the action space, per-action risk, disabled paths, and the settings object well. The remaining gap is return-value shape: an agent gets no hint about what status/devices/topology/clients yield, which matters since there is no output schema to fall back on.

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 55% schema coverage the description must carry weight, and it does: it enumerates the nested settings keys (name, location, led, preferred_wifi_uplink_ap, traffic_separation, backhaul_steering) that the schema leaves as an opaque object, and clarifies for bind_client that mac means the unit while client_mac is the client being pinned, plus bind=true|false meaning. It leaves wait, apply, reveal, router and confirm_token entirely to the schema, which does describe them.

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 names the domain (EasyMesh) and enumerates the exact action set the tool dispatches (status, devices, clients, topology, pair, bind_client, etc.), so an agent knows precisely what surface it covers. It does not explicitly distinguish itself from sibling tools like extender or extender_set, which leaves some ambiguity about which mesh/AP tool to reach for.

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 guidance is embedded per action rather than stated as a routing rule: 'disable (CRITICAL if satellites are attached)', 'rebalance (clients re-pick the best unit)', and 'pair (DISABLED... use the web UI / Tether / WPS button)' each tell the agent when an action is dangerous or unavailable. However, it never says when to prefer this tool over siblings such as extender_set, or which read action (status vs devices vs topology) answers which question.

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