Skip to main content
Glama

maintenance

Destructive

Perform TP-Link router upkeep: back up/restore configs, check or update firmware, run ping/traceroute, change operation mode, schedule reboots, with dry-run safety.

Instructions

Maintenance. action=info | backup (download the config to the backup folder) | backups (list) | restore (file = a backup name or path; CRITICAL, reboots) | firmware_check (router + mesh satellites, online) | firmware_update_online (CRITICAL, reboots) | firmware_status | firmware_upload (file = image path; CRITICAL) | satellite_firmware_update (mac) | ping / traceroute (target, count, size, max_hops, timeout) | operation_mode (mode=router|ap|repeater|client|multissid; none = read; CRITICAL; keep_access) | reboot_schedule (settings). Factory reset is deliberately only reachable via router_raw_write (forbidden tier).

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": "maintenance"
  }
}

Input Schema

NameRequiredDescriptionDefault
macNo
fileNo
modeNo
sizeNo
applyNofalse (default) = dry run: show the plan, diff, warnings and risk, send nothing. true = send it.
countNo
actionNoinfo
revealNoShow secrets (passwords/keys) unmasked.
routerNoWhich router (see router_status 'routers'); default main.main
targetNo
timeoutNo
max_hopsNo
settingsNofields to change (see the matching router_catalog form)
keep_accessNooperation_mode to router: turn remote management on first so this server can reach the device on its WAN side (exposes the admin page there - the internet if the WAN is your ISP)
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

A4/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and non-idempotent, and the description adds real specifics beyond them: which actions are CRITICAL and reboot the device (restore, firmware_update_online, firmware_upload), that operation_mode is CRITICAL and that keep_access exposes the admin page on the WAN side. That last warning is exactly the kind of consequence disclosure annotations cannot convey. It stops short of describing auth requirements, timing, or what the backup/restore actually touches, so it is not exhaustive.

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?

A single pipe-delimited block where every clause carries information — no filler sentences. It is front-loaded with the action list and closes with the factory-reset exclusion. The density makes it harder to scan than a line-per-action layout, which is the only real cost.

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 15-parameter multiplexed tool with no output schema, the definition covers the action space, destructive consequences, and the two-parameter (apply/confirm_token) safety gate well enough to invoke correctly. It does not say what info/backups/firmware_status return or where the backup folder lives, but those are recoverable from calling the read-only actions first.

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 40% across 15 parameters, so the description must compensate, and it does for the highest-risk ones: `file` is disambiguated as 'a backup name or path' for restore versus 'image path' for firmware_upload, `mac` is tied to satellite_firmware_update, the ping/traceroute bundle (target, count, size, max_hops, timeout) is grouped, and `mode`'s 'none = read' semantics are stated. Gaps remain for reveal, router, and confirm_token, though the schema itself documents those.

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 a specific resource (router maintenance) and enumerates each supported action with a short gloss (backup, restore, firmware_check, ping/traceroute, operation_mode, reboot_schedule), so an agent can map intent to action without opening the schema. It also distinguishes itself from router_raw_write by noting factory reset is deliberately only reachable there. The bare opening word 'Maintenance' restates the tool name, but the action list carries the real purpose.

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?

Per-action parentheticals give concrete selection cues (e.g. 'backups (list)' vs 'backup (download the config)', 'firmware_check (router + mesh satellites, online)' vs 'firmware_status'). It states the explicit exclusion that factory reset is only available via router_raw_write and is forbidden here. It does not, however, say when to prefer this tool over siblings like system, admin, or mesh for overlapping operations.

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