Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

evaluate_fleet_reroute

Read-only

Decides if a failed FDM job should move to another printer by checking progress, material, build volume, idle status, and success rate; returns blocked when no alternatives exist.

Instructions

Decide whether a failed FDM job should move to another printer (Business+).

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": {
      "failure_id": "<failure_id>",
      "alternative_printers": "<alternative_printers>"
    },
    "name": "evaluate_fleet_reroute"
  }
}

Input Schema

NameRequiredDescriptionDefault
materialNoMaterial the job needs (e.g. ``"pla"``, ``"petg"``). Candidates whose ``supported_materials`` doesn't include this are filtered out. Empty string disables material matching. Default: "".
failure_idYesID returned by ``detect_print_failure``. The original printer + failure_type are read from the stored failure report.
model_size_mmNoOptional ``[x, y, z]`` model envelope in mm. Candidates whose explicit or auto-resolved ``build_volume_mm`` is too small on any axis are filtered out.
completion_pctNoHow far the failed print got (0.0–1.0). A print that had barely started is restarted on the same machine rather than moved; the decision says which way it went. Default: 0.0.
alternative_printersYesList of candidate printer dicts. Each must include ``printer_id``; optional fields: ``is_idle`` (default True), ``supported_materials`` (list of material strings), ``build_volume_mm`` (3-tuple of floats; auto-resolved from ``printer_id`` for supported models when omitted), ``success_rate`` (0.0–1.0 from learning engine). Empty list returns a NO_ALTERNATIVES blocked decision.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv1.5.1
    • addedInput schema / properties / alternative_printers / description
      Added value: +"List of candidate printer dicts. Each must include ``printer_id``; optional fields: ``is_idle`` (default True), ``supported_materials`` (list of material strings), ``build_volume_mm`` (3-tuple of floats; auto-resolved from ``printer_id`` for supported models when omitted), ``success_rate`` (0.0–1.0 from learning engine). Empty list returns a NO_ALTERNATIVES blocked decision."
    • changedInput schema / properties / completion_pct / description
      Previous value: -"Default: 0.0."New value: +"How far the failed print got (0.0–1.0).  A print that had barely started is restarted on the same machine rather than moved; the decision says which way it went. Default: 0.0."
    • addedInput schema / properties / failure_id / description
      Added value: +"ID returned by ``detect_print_failure``. The original printer + failure_type are read from the stored failure report."
    • changedInput schema / properties / material / description
      Previous value: -"Default: \"\"."New value: +"Material the job needs (e.g. ``\"pla\"``, ``\"petg\"``).  Candidates whose ``supported_materials`` doesn't include this are filtered out.  Empty string disables material matching. Default: \"\"."
    • addedInput schema / properties / model_size_mm / description
      Added value: +"Optional ``[x, y, z]`` model envelope in mm.  Candidates whose explicit or auto-resolved ``build_volume_mm`` is too small on any axis are filtered out."
  2. Addedv1.5.0

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description's decision-only framing is consistent and the safety profile is covered. It adds real value by disclosing the Business+ entitlement requirement. However, it says nothing about what the decision returns (e.g., a blocked NO_ALTERNATIVES outcome) or that calling it does not actually perform the reroute.

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?

A single front-loaded sentence with no padding and the tier constraint attached inline. It is appropriately sized for a headline, though a second clause on outcome or prerequisites would have earned its place.

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?

There is no output schema and five parameters, so the description carries some burden for explaining the decision result and the restart-vs-move branching logic. The rich parameter documentation partially compensates, but the definition alone leaves an agent guessing what the tool returns and whether it acts or only advises.

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 every parameter including alternative_printers, completion_pct, and material is documented in detail upstream. The description adds nothing beyond that, which is acceptable given the baseline but earns no extra credit.

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?

"Decide whether a failed FDM job should move to another printer" names a specific verb (decide) and resource (failed job / printer reassignment), so an agent can tell this is a decision/advisory tool rather than an action tool like route_print_job or fleet_submit_job. It stops short of naming those siblings explicitly, so the boundary must be inferred.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The only usage signal is the "(Business+)" tier gate. There is no statement of when to call this versus route_print_job, suggest_printer_for_job, or plan_failure_recovery, nor any prerequisite that a failure must first be detected. Schema parameter text mentions detect_print_failure, but that is not in the description and does not count.

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