Skip to main content
Glama

create_queue_type

Creates a queue type (qdisc) on MikroTik RouterOS by selecting a discipline (cake, fq-codel, sfq, red, pcq, pfifo, bfifo) and setting per-discipline options for traffic shaping.

Instructions

Creates a queue type (qdisc). kind selects the discipline (cake, fq-codel, sfq, red, pcq, pfifo, bfifo); remaining params are per-discipline options.

Notes: pcq_rate: bandwidth per flow e.g. "1M", "512k" pcq_classifier: comma-separated classifiers e.g. "src-address,dst-address" cake_rtt: round-trip time e.g. "50ms", "100ms" fq_codel_target / fq_codel_interval: time e.g. "5ms", "100ms"

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": {
      "name": "<name>"
    },
    "name": "create_queue_type"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNocake
nameYes
deviceNo
cake_mpuNo
cake_natNo
cake_rttNo
pcq_rateNo
cake_washNo
pcq_limitNo
red_burstNo
red_limitNo
sfq_allotNo
bfifo_limitNo
pfifo_limitNo
sfq_perturbNo
cake_diffservNo
cake_flowmodeNo
cake_overheadNo
fq_codel_limitNo
pcq_classifierNo
red_avg_packetNo
cake_ack_filterNo
fq_codel_targetNo
fq_codel_quantumNo
fq_codel_intervalNo
red_max_thresholdNo
red_min_thresholdNo
cake_overhead_schemeNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.14.5
    • addedInput schema / properties / device
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Device"
      +}
  2. First observedv0.0.0

TDQS

B3.3/5.0
Behavior3/5

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

Annotations already disclose the mutation profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=false), so the description's job is supplementary. It delivers on that partly by naming the valid disciplines and giving value-format examples (pcq_rate "1M"/"512k", cake_rtt "50ms", fq_codel_target "5ms"), which is exactly the context the bare schema lacks. It does not say what happens on a name collision, whether the change is immediately applied to live traffic, or what the response contains.

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 one-sentence core, then a compact indented notes block for value formats — no filler sentences. The note list is slightly uneven, since it spotlights a handful of params out of 28 with no stated selection principle, but nothing is redundant.

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?

Placeholder evaluation: this should be 2 given 28 parameters, 0% schema coverage, and only partial notes. Correcting: the description leaves most of a very large parameter surface unexplained, which is a real gap for an agent constructing a qdisc definition. The output schema does cover return values, so that gap is absolved, but the input side remains under-specified.

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% across 28 parameters, so the description carries the full burden and only covers about six of them (kind, pcq_rate, pcq_classifier, cake_rtt, fq_codel_target, fq_codel_interval). The unit hints it does give are genuinely valuable because they disambiguate otherwise cryptic names. But the majority of params (cake_mpu, cake_nat, cake_wash, pcq_limit, all red_*, sfq_*, pfifo_limit, bfifo_limit, cake_overhead_scheme) get no explanation of units or meaning, and the enum values for kind in the schema exceed those listed in the description.

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?

States a specific verb and resource ("Creates a queue type") and adds the domain term qdisc, so the agent knows this is the create-side counterpart to get/update/remove_queue_type. It also explains the role of the `kind` parameter as the discipline selector, which is the key structural fact about the tool. It stops short of explicitly naming the sibling to use for modification, but the verb makes that inference safe.

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?

Gives useful in-tool guidance: `kind` chooses the discipline and "remaining params are per-discipline options," which steers the agent to send only the options matching the chosen kind. There is no explicit when-to-use versus update_queue_type, no statement that creating an existing name fails, and no prerequisites about the target device. Usage is implied rather than stated.

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