Skip to main content
Glama

clients

Destructive

Manage connected devices on TP-Link routers by listing, renaming, setting speed limits, accelerating games, and isolating smart-home devices on an IoT network.

Instructions

Connected devices. action=list | rename (mac, name: the name shown everywhere) | speed (limits/speeds) | speed_limit (mac, download_kbps, upload_kbps, enable) | game_accelerator | iot_status | iot_enable | iot_disable | iot_add / iot_remove (mac or macs: move smart-home devices to the isolated IoT network).

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": "clients"
  }
}

Input Schema

NameRequiredDescriptionDefault
macNo
macsNo
nameNo
applyNofalse (default) = dry run: show the plan, diff, warnings and risk, send nothing. true = send it.
actionNolist
enableNo
revealNoShow secrets (passwords/keys) unmasked.
routerNoWhich router (see router_status 'routers'); default main.main
upload_kbpsNo
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).
download_kbpsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, so the safety bar is lower. The description adds real context by explaining that iot_add/iot_remove physically relocate devices to an isolated IoT network and that rename changes the name "shown everywhere", but it never flags which specific actions are destructive or that critical changes require the dry-run/confirm_token workflow.

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?

It is compact and front-loaded with the resource, and no sentence is filler. But the pipe-and-slash telegraphic style makes parsing hard, and the parentheticals mix parameter documentation with behavioral semantics without a consistent pattern.

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 an 11-parameter, multi-action, destructive tool with no output schema, the description covers the action surface but omits the two-stage apply/confirm_token safety flow and which actions are critical. An agent could invoke a destructive action without realizing a dry run is expected, relying entirely on the schema to discover that.

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 only 36% schema description coverage across 11 parameters, the description does meaningful work by mapping parameters to actions (rename takes mac+name, speed_limit takes mac+download_kbps+upload_kbps+enable, iot_add/remove take mac or macs). That action-to-parameter mapping exists nowhere in the schema. It does not, however, clarify when `macs` vs `mac`, or which actions consume `enable` in the speed context.

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 a concrete resource ("Connected devices") and enumerates the full action surface, so an agent knows this is the client/device management tool. However, several action glosses are cryptic ("speed (limits/speeds)", bare "game_accelerator") and it never contrasts itself with siblings like device_log or ip_mac_binding.

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 is implied only through the action menu: an agent can infer that `list` enumerates and `iot_add`/`iot_remove` move smart-home devices to an isolated network. There is no explicit when-to-use vs when-not guidance, no prerequisites, and no pointer to sibling tools for adjacent tasks.

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