Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

detect_print_failure

Destructive

Analyze printer telemetry and recent history to identify and classify 3D print failures such as thermal runaway, layer shift, filament runout, adhesion loss, or nozzle clogs for recovery planning.

Instructions

Analyze printer telemetry to detect and classify a print failure.

        Examines current telemetry data and optional historical snapshots
        to identify failure conditions such as thermal runaway, layer shift,
        filament runout, adhesion loss, nozzle clogs, and more.

        The readings passed here are judged, not announced: a failure
        found in them is kept (for ``plan_failure_recovery``) and marked
        ``readings_from: "caller"``, but no failure alert goes out and the
        printer's own print watchdog keeps running.  Only readings Kiln
        takes off the printer itself, while it watches a print, announce
        a failure.

        Args:
            printer_name: Identifier of the printer to analyze.
            telemetry: Current telemetry snapshot with keys like
                ``hotend_temp``, ``bed_temp``, ``connected``,
                ``filament_detected``, etc.
            telemetry_history: Optional list of recent telemetry snapshots
                for trend analysis (newest last).
            job_info: Optional current job metadata with keys like
                ``file_name``, ``layer``, ``total_layers``, ``z_mm``.

        Returns a failure report dict if a failure is detected, or a
        success dict with ``failure_detected: False`` if no failure found.

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": {
      "printer_name": "<printer_name>",
      "telemetry": "<telemetry>"
    },
    "name": "detect_print_failure"
  }
}

Input Schema

NameRequiredDescriptionDefault
job_infoNoOptional current job metadata with keys like ``file_name``, ``layer``, ``total_layers``, ``z_mm``.
telemetryYesCurrent telemetry snapshot with keys like ``hotend_temp``, ``bed_temp``, ``connected``, ``filament_detected``, etc.
printer_nameYesIdentifier of the printer to analyze.
telemetry_historyNoOptional list of recent telemetry snapshots for trend analysis (newest last).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv1.5.1
    • addedInput schema / properties / job_info / description
      Added value: +"Optional current job metadata with keys like ``file_name``, ``layer``, ``total_layers``, ``z_mm``."
    • addedInput schema / properties / printer_name / description
      Added value: +"Identifier of the printer to analyze."
    • addedInput schema / properties / telemetry / description
      Added value: +"Current telemetry snapshot with keys like ``hotend_temp``, ``bed_temp``, ``connected``, ``filament_detected``, etc."
    • addedInput schema / properties / telemetry_history / description
      Added value: +"Optional list of recent telemetry snapshots for trend analysis (newest last)."
  2. Changed2 schema fields changedv1.5.0
    • removedInput schema / properties / job_info / default
      Removed value: -null
    • removedInput schema / properties / telemetry_history / default
      Removed value: -null
  3. First observedv0.1.0

TDQS

A3.6/5.0
Behavior4/5

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

The description adds substantial behavioral context beyond the annotations: caller readings are not announced, the printer's own watchdog keeps running, and a detected failure is retained for plan_failure_recovery with readings_from set to caller. These details explain the non-alerting side effect and persistence behavior. It does not fully explain why the tool carries destructiveHint=true, but it does not contradict that annotation.

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 description is front-loaded with a clear purpose statement and useful behavioral contrast, but it redundantly restates the parameter descriptions already present in the schema. The Args and Returns blocks add length without all sentences earning their place, though the overall structure is readable.

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?

With no output schema, the description explains the return behavior at a high level: a failure report dict if detected, or a success dict with failure_detected false otherwise. Combined with annotations and full parameter coverage, this is largely complete, though it could say more about the failure report structure and sibling differentiation.

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 description coverage is 100%, so the schema already documents printer_name, telemetry, telemetry_history, and job_info with the same example keys and semantics. The description repeats this information in an Args block without adding meaning beyond what the schema provides, so the baseline of 3 is appropriate.

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 states a specific verb and resource: analyze printer telemetry to detect and classify a print failure, with concrete failure examples such as thermal runaway, layer shift, filament runout, adhesion loss, and nozzle clogs. The purpose is clear, but it does not distinguish itself from the many sibling failure-analysis tools like analyze_print_failure, diagnose_print_failure_live, or predict_print_failure.

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?

The description implies usage through the contrast between caller-supplied readings, which are judged but not announced, and Kiln-acquired readings, which do announce a failure. It also mentions the failure is kept for plan_failure_recovery. However, it does not explicitly say when to use this tool versus sibling alternatives or name any exclusions.

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