Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

record_recovery_outcome

Record how a 3D-print recovery went by logging failure type, recovery strategy, success, timing, and notes so Kiln can track outcomes and settle watched recoveries.

Instructions

Tell Kiln how a recovery went (free at every tier).

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_type": "<failure_type>",
      "strategy": "<strategy>",
      "success": "<success>"
    },
    "name": "record_recovery_outcome"
  }
}

Input Schema

NameRequiredDescriptionDefault
notesNoKept only in this computer's own record, never on your account. Default: "".
successYesWhether the recovery ultimately succeeded.
strategyYesOne of ``resume_from_layer``, ``restart_with_compensation``, ``partial_recovery``, ``safe_abort``, ``wait_and_retry``, ``no_recovery``, ``skip_failed_objects``, ``moved_to_another_printer``, ``unknown``.
session_idNoOptional recovery session ID from public Kiln (a session reported twice on this computer stays one). Default: "".
failure_typeYesOne of ``layer_shift``, ``thermal_runaway``, ``filament_runout``, ``adhesion_failure`` (``adhesion_loss`` is read as it), ``blob_detected``, ``power_loss``, ``nozzle_clog``, ``spaghetti``, ``stringing``, ``warping``, ``communication_loss``, ``unknown``.
printer_nameNoThe printer, as your Kiln names it. Needed to settle a recovery Kiln is watching. Default: "".
material_typeNoOptional material (``"pla"``, etc.). Default: "".
time_to_resolve_sNoTotal time spent on recovery. Default: 0.0.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.5.1

TDQS

C2.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, so the write/no-side-effect profile is covered structurally. The description contributes one genuine behavioral fact the annotations do not: the call is free at every tier, so it carries no billing or spend-cap risk. It omits whether repeated calls are idempotent, whether it needs an active recovery session, and what effect recording has on later strategy statistics.

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 short sentence, front-loaded with the verb and resource, with zero redundant wording. It is efficient, though the brevity borders on under-specification rather than tight editing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is an 8-parameter write operation in a crowded recovery/outcome-recording family, and the description says nothing about how it relates to record_recovery_check, complete_print_recovery, or get_recovery_strategy_stats, nor what recording enables downstream. No output schema exists, so the description should carry more of that relational and behavioral load than one parenthetical sentence.

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%, with enumerated failure_type and strategy values, defaults, and the local-only note on notes all documented in the schema itself. The description adds no meaning beyond that, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Tell Kiln how a recovery went" identifies the operation as recording the outcome of a recovery, but it is informal and does not name the tuple actually captured (failure type, strategy, success, time to resolve). It also fails to distinguish this from nearby siblings such as record_recovery_check, complete_print_recovery, or record_print_outcome, which an agent must disambiguate without help.

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 guidance offered is "(free at every tier)", which is pricing information rather than a when-to-use rule. There is no statement of prerequisites, no condition for choosing this over complete_print_recovery or record_recovery_check, and no note on whether a session must already exist.

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