Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

record_bond_outcome

Record whether a glued joint held, failed, or partially held, capturing adhesive and material details so Kiln can learn from past bond outcomes.

Instructions

Record whether a glued joint held or failed — so Kiln learns over time.

Needs Kiln Pro.

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": {
      "material_a": "<material_a>",
      "adhesive": "<adhesive>",
      "result": "<result>"
    },
    "name": "record_bond_outcome"
  }
}

Input Schema

NameRequiredDescriptionDefault
notesNoAnything else worth capturing. Default: "".
resultYes"held" | "failed" | "partial".
adhesiveYesThe adhesive used (e.g. "Loctite 401", "2-part epoxy").
design_idNoDesign this bond belongs to, if any (links the outcome to the design's history). Default: "".
material_aYesFirst bonded material (e.g. "PETG").
material_bNoSecond material. Omit if both parts are the same. Default: "".
printer_idNoPrinter that made the parts. Defaults to "default". Default: "default".
environmentNoWhere/how it was stressed (e.g. "indoor", "60C", "outdoor", "submersion"). Default: "".
failure_modeNoIf it failed: ``"peel"``, ``"shear"``, ``"impact"`` or ``"cohesive"`` (the glue line itself); leave empty if it held. Default: "".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changedv1.5.1
    • addedInput schema / properties / adhesive / description
      Added value: +"The adhesive used (e.g. \"Loctite 401\", \"2-part epoxy\")."
    • changedInput schema / properties / design_id / description
      Previous value: -"Default: \"\"."New value: +"Design this bond belongs to, if any (links the outcome to the design's history). Default: \"\"."
    • changedInput schema / properties / environment / description
      Previous value: -"Default: \"\"."New value: +"Where/how it was stressed (e.g. \"indoor\", \"60C\", \"outdoor\", \"submersion\"). Default: \"\"."
    • changedInput schema / properties / failure_mode / description
      Previous value: -"Default: \"\"."New value: +"If it failed: ``\"peel\"``, ``\"shear\"``, ``\"impact\"`` or ``\"cohesive\"`` (the glue line itself); leave empty if it held. Default: \"\"."
    • addedInput schema / properties / material_a / description
      Added value: +"First bonded material (e.g. \"PETG\")."
    • changedInput schema / properties / material_b / description
      Previous value: -"Default: \"\"."New value: +"Second material.  Omit if both parts are the same. Default: \"\"."
    • changedInput schema / properties / notes / description
      Previous value: -"Default: \"\"."New value: +"Anything else worth capturing. Default: \"\"."
    • changedInput schema / properties / printer_id / description
      Previous value: -"Default: \"default\"."New value: +"Printer that made the parts.  Defaults to \"default\". Default: \"default\"."
    • addedInput schema / properties / result / description
      Added value: +"\"held\" | \"failed\" | \"partial\"."
  2. Addedv1.5.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare this is a non-read-only, non-destructive, closed-world write, so the safety profile is covered. Beyond that the description discloses two things the annotations do not: a tier gate ("Needs Kiln Pro") and that the record feeds a learning loop. It does not say whether repeated recordings are deduplicated or how the record affects future recommendations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, zero waste, purpose stated first and the tier prerequisite front-loaded as its own line. Every sentence earns 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?

With nine parameters, no output schema, and full schema documentation, the description covers the essentials but is thin for a write tool that feeds a learning system: it does not state what is returned or how the outcome propagates into recommendations. Adequate but with clear gaps.

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 all nine parameters documented, including examples and defaults, so the schema carries the semantic burden. The description adds nothing about individual fields and slightly narrows the result set by saying "held or failed" when the schema also accepts "partial". Baseline 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?

"Record whether a glued joint held or failed" names a specific verb and resource, and the adhesive domain distinguishes it from the many sibling record_* outcome tools (record_load_outcome, record_magnet_outcome, record_hardware_outcome). It stops short of explicitly routing the agent away from those siblings, so it is clear but not fully differentiated.

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 phrase "so Kiln learns over time" implies this is called after a real-world bond test, and "Needs Kiln Pro" is a genuine prerequisite worth knowing. However, there is no explicit when-to-use framing, no mention of when not to record, and no pointer to alternatives such as recommend_adhesive or the other record_*outcome tools.

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