Skip to main content
Glama

ont_run

Runs one ONT CLI command to apply configuration changes, requiring local human approval and typed confirmation for high-impact actions; include a reason and save before reboot.

Instructions

Run a command that changes the ONT (config ..., save, reboot, ...). Before it runs, the person at the computer sees a dialog naming the ONT, the command and its risk, and must type a confirmation word; you cannot answer it. High-impact commands (reboot, reset, restore, firmware, WAN/LAN/PPP/VLAN, accounts, remote access) need that word typed. Explain in 'reason' why the change is needed. Many ONTs need a save command (for example 'config save') before a change survives a reboot.

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": "ont_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
reasonNoWhy, shown in the dialog.
commandYesOne CLI command.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the full behavioral burden and does so well: it discloses the human confirmation dialog, that the agent cannot answer it, that high-impact categories (reboot, reset, firmware, WAN/LAN/PPP/VLAN, accounts, remote access) require a typed confirmation word, and the persistence caveat about save. It omits anything about permissions, failure modes, or what the call returns.

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?

The text is dense and front-loaded, leading with what the tool does and the human-confirmation constraint. The reboot/save sentence is slightly tacked on but carries real operational value, so it earns its place.

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 two-parameter mutation tool with no annotations and no output schema, the description supplies the crucial behavioral context: the confirmation dialog, risk categories, and the save requirement. What is missing is what a successful or rejected call returns, which matters more here because no output schema exists.

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

Parameters3/5

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

Schema coverage is 100%, so both parameters are already documented. The description only restates that 'reason' explains why (shown in the dialog) and that command is a single CLI command, which is already in the schema descriptions. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb+resource ('Run a command that changes the ONT') and gives concrete examples (config, save, reboot). This clearly separates it from the sibling read/info tools ont_show and ont_help without needing their schemas.

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?

It clearly establishes the context of use: any change to the ONT goes through this tool, and a human must confirm. It also adds a domain-specific sequencing rule (run 'config save' before a reboot for persistence). It stops short of explicitly telling the agent to inspect state first via ont_show, so not a 5.

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

Deploy Server

Other Tools