Skip to main content
Glama

ros_command

Run RouterOS API commands with full paths and parameters to configure, monitor, and troubleshoot MikroTik routers.

Instructions

Run ANY RouterOS API command: full path including the verb. Examples: '/system/reboot', '/tool/ping' {'address': '8.8.8.8', 'count': 3}, '/ip/firewall/filter/move' {'numbers': '*5', 'destination': '*2'}, '/system/package/update/check-for-updates', '/interface/monitor-traffic' {'interface': 'ether1', 'once': ''}, '/tool/traceroute' {'address':'1.1.1.1','count':1}. Long-running commands need 'count' / 'once' / 'duration' so they end.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "command": "<command>"
    },
    "name": "ros_command"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryNo
paramsNo
routerNo
commandYes
proplistNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior3/5

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

With no annotations, the description carries the full burden. It does disclose a real behavioral trait — that long-running commands will hang unless bounded by count/once/duration — which is genuinely useful. However, it never warns that this tool can execute destructive operations ('/system/reboot' is literally the first example), says nothing about permissions/authentication requirements, and gives no sense of what the response looks like for arbitrary commands.

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?

Front-loaded with the core rule, followed by dense worked examples, and closed with the operational caveat about long-running commands. The examples are informative rather than filler, though six of them is on the verbose side and the line breaks in the raw text make it slightly harder to parse.

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?

An output schema exists, so return values need not be explained, and the examples make the 'command'/'params' pairing clear. But for a five-parameter arbitrary-command executor with no annotations, leaving router selection, query, and proplist undefined is a real completeness gap an agent would trip over.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, and it only explains two of five parameters: 'command' as the full path including the verb, and 'params' as the argument dict (shown in examples). The 'router', 'query', and 'proplist' parameters — including how to target a specific router and what query/proplist filtering syntax is expected — are left entirely undocumented.

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 gives a specific verb and resource ('Run ANY RouterOS API command: full path including the verb') and supplies six concrete command examples spanning reboot, ping, firewall move, package update, traffic monitor, and traceroute. The word 'ANY' signals this is the generic escape hatch, but it never names the typed siblings (ros_print, ros_set, ros_add) it supersedes.

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 rather than stated: the breadth of examples suggests 'use this when a specialized tool doesn't cover the operation,' but no explicit when-to-use or when-not-to-use rule appears. The only concrete guidance is the closing rule that long-running commands need 'count'/'once'/'duration' to terminate.

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