Skip to main content
Glama

torch

Read-only

Shows live per-flow traffic rates on a MikroTik interface for a few seconds, with optional filters to break down traffic by address, protocol, port, VLAN, or DSCP.

Instructions

Shows live traffic rates per flow on an interface for a few seconds (needs the "sniff" policy).

Notes: Each filter both filters and breaks the table down by that field: "0.0.0.0/0" (or "::/0") lists every address, "any" every protocol/port/VLAN/DSCP. With no filter, flows are broken down by IPv4 src/dst address and IP protocol. Torch turns off fasttrack while it runs (higher CPU). RouterOS prints its first frame after two seconds, so a duration under 3 runs for 3.

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": {
      "interface": "<interface>"
    },
    "name": "torch"
  }
}

Input Schema

NameRequiredDescriptionDefault
dscpNo
portNo
deviceNo
vlan_idNo
durationNo
interfaceYes
dst_addressNo
ip_protocolNo
src_addressNo
dst_address6No
mac_protocolNo
src_address6No

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.29.1

TDQS

A4.1/5.0
Behavior4/5

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

Annotations declare readOnlyHint/openWorldHint, but the description adds genuinely non-obvious behavior: torch disables fasttrack while running (CPU impact), RouterOS emits its first frame only after two seconds, and durations below 3 are silently raised to 3. Those side effects and silent clamping are the kind of context an agent cannot get from the schema. It stops short of describing output shape, though an output schema exists.

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 core behavior is front-loaded in one sentence and the notes are terse, each conveying a distinct operational fact. The wildcard-sentinel sentence is dense but earns its place; minor verbosity in the '::/0' parenthetical.

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 12-parameter sampling tool, the description covers the prerequisite, the side effect, the timing behavior, and the filter/wildcard conventions, and an output schema exists so return values need not be described. Remaining gap is per-parameter guidance for the non-filter fields.

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 0% across 12 parameters, so the description must carry the load; it does explain the shared filter semantics ('each filter both filters and breaks the table down by that field', with '0.0.0.0/0', '::/0', 'any' as wildcards) and the default breakdown when no filter is given. However, it never addresses device, mac_protocol, dscp, vlan_id, or the per-field distinctions, and only touches duration via the 3-second clamp.

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 names a specific verb and resource ('Shows live traffic rates per flow on an interface') plus the time window and a required prerequisite ('needs the "sniff" policy'). No sibling tool in the catalog does packet-rate sampling, so the agent can identify this tool immediately without opening the schema.

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 states the prerequisite for use (the 'sniff' policy must be enabled) and a practical constraint for the duration argument. It does not name alternatives or when-not-to-use conditions, but no comparable sibling exists, so the absence is minor.

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