Skip to main content
Glama

FrontierStack by Enfour, Inc.

Run a read-only diagnostic

diagnose
Read-onlyIdempotent

Run one bounded, read-only diagnostic program on the selected Mac or a linked server. Arguments are passed directly, never through a shell, and time limits are applied. argv[0] must be one of: ping, ping6, dig, nslookup, host, traceroute, nc (with -z), curl (GET/HEAD), ifconfig, netstat, route, arp, ipconfig (get* only), networksetup (read-only queries), scutil, sysctl, df, uptime, vm_stat, uname, sw_vers, brew (list/info/services list), apachectl configtest, nginx -t, php (-v/-m/-i/--ini/-l), php-config; on Linux targets also nvme, iscsiadm, lsscsi, multipath -ll and InfiniBand status tools. ["oclp"] returns a macOS update-safety report for Macs using OpenCore Legacy Patcher. Anything else is refused by the Mac.

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": {
      "argv": "<argv>"
    },
    "name": "diagnose"
  }
}

Input Schema

NameRequiredDescriptionDefault
argvYesProgram and arguments, e.g. ["dig","example.com","MX"] or ["uptime"].
mac_idNoOpaque id of one of this account's FrontierStack Macs. Optional only when exactly one Mac is online.
targetNoOptional linked server, by the name or host FrontierStack knows it by, to run on over SSH. Omit for the selected Mac itself.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / mac_id / description
      Previous value: -"Opaque Mac id returned by list_frontierstack_macs. Optional only when exactly one Mac is online."New value: +"Opaque id of one of this account's FrontierStack Macs. Optional only when exactly one Mac is online."
    • changedInput schema / properties / target / description
      Previous value: -"Optional linked server (its name or host as shown in get_fleet_context) to run on over SSH. Omit for the selected Mac itself."New value: +"Optional linked server, by the name or host FrontierStack knows it by, to run on over SSH. Omit for the selected Mac itself."
  2. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, and the description adds real context beyond that: no shell interpolation, applied time limits, server-side refusal of anything off-list, and different permitted programs for macOS vs Linux targets. The notable omission is any statement of what the call returns (stdout/stderr, exit status, truncation, time-limit behavior), which matters for an open-world exec tool.

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?

The opening sentence is well front-loaded and earns its place. However, the allowlist is delivered as a single dense run-on paragraph mixing macOS programs, Linux extras and a stray ['oclp'] special-case sentence at the end, which is hard to scan and would be far clearer as structured bullets separated from the invocation rules.

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 a complex, open-world execution tool with no output schema, the definition covers invocation constraints well but leaves the return side entirely undefined except for the ['oclp'] report. An agent cannot tell how output is delivered (stdout, exit code, truncation, time-limit exceeded signaling), which is exactly the gap the description must fill when no output schema exists.

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 100%, so the baseline is 3, but the description meaningfully constrains argv beyond the schema's generic string array: argv[0] must come from an enumerated allowlist, arguments bypass the shell, and per-program restrictions apply (nc requires -z, curl limited to GET/HEAD, ifconfig/netstat read-only). The mac_id 'optional only when exactly one Mac is online' rule and the target-over-SSH distinction reinforce the schema rather than add much, keeping it short of a 5.

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 first sentence states a precise verb and resource — run one bounded, read-only diagnostic program — plus scope (single invocation, Mac or linked server). Among siblings like read_logs, get_server_health and service_action, it is unambiguous that this is the arbitrary-probe execution tool rather than a structured telemetry reader.

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?

It defines the hard boundary — the argv[0] allowlist and 'anything else is refused' — which is genuinely useful selection guidance. But it never says when to prefer this over read_logs, get_server_health or get_alert_errors, nor when a diagnostic is inappropriate; the agent must infer that from sibling names alone.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.