Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

recommend_design_reinforcements

Read-only

Analyze an STL mesh to find structural risks and recommend specific reinforcements—gussets, fillets, wall thickening, base widening, or reorientation—with coordinates and next tool.

Instructions

Recommend specific reinforcements for an STL mesh.

        Analyzes geometry to find structural risks, then generates actionable
        recommendations with **specific locations** and what each one does for the part:
        - **gusset**: triangular support at cantilever bases
        - **fillet**: smooth transitions at stress concentrations
        - **thicken_wall**: add material at thin necks
        - **add_base**: widen the base for stability
        - **reorient**: change print orientation for layer strength

        Each recommendation includes the coordinates where the reinforcement
        should be applied and which Kiln tool to use (e.g., ``add_mesh_fillet()``).

        A file smaller than anything a printer makes is answered with
        ``units_question`` and no recommendation.

        :param file_path: Path to the STL file.
        :param min_cross_section_mm2: Minimum safe cross-section area.
            Leave unset for Kiln's own threshold.
        :returns: Dict with ``reinforcements`` list.

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": {
      "file_path": "<file_path>"
    },
    "name": "recommend_design_reinforcements"
  }
}

Input Schema

NameRequiredDescriptionDefault
file_pathYesPath to the STL file.
min_cross_section_mm2NoMinimum safe cross-section area. Leave unset for Kiln's own threshold.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv1.5.1
    • addedInput schema / properties / file_path / description
      Added value: +"Path to the STL file."
    • addedInput schema / properties / min_cross_section_mm2 / anyOf
      Added value: +[
+  {
+    "type": "number"
+  },
+  {
+    "type": "null"
+  }
+]
    • changedInput schema / properties / min_cross_section_mm2 / description
      Previous value: -"Default: 4.0."New value: +"Minimum safe cross-section area. Leave unset for Kiln's own threshold."
    • removedInput schema / properties / min_cross_section_mm2 / type
      Removed value: -"number"
  2. Changed2 schema fields changedv1.5.0
    • removedInput schema / properties / min_cross_section_mm2 / default
      Removed value: -4
    • addedInput schema / properties / min_cross_section_mm2 / description
      Added value: +"Default: 4.0."
  3. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already establish safe read-only behavior, and the description adds real behavioral detail beyond them: it discloses that geometry analysis drives the output, that each recommendation carries coordinates plus a target Kiln tool, and that an undersized file yields a units_question with no recommendation. That documented edge-case output is exactly the kind of behavior an agent cannot get from readOnlyHint/destructiveHint.

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?

Front-loaded purpose sentence, then a scannable bullet list for each reinforcement type with its meaning, then output and edge-case notes. No filler, and the schema params are tacked on at the end rather than interrupting the core explanation.

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?

For a two-parameter read-only tool with no output schema, the description covers the return shape ('Dict with reinforcements list'), the content of each entry, and the degenerate-input case. Only minor gaps remain, such as whether recommendations are ranked or capped and what the units_question payload looks like.

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?

With 100% schema description coverage the baseline is 3, and the description merely restates the two schema parameter docs verbatim ('Path to the STL file', 'Leave unset for Kiln's own threshold') without adding format, units, or interaction guidance.

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

Purpose5/5

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

The opening sentence names a specific verb and resource ('Recommend specific reinforcements for an STL mesh') and the bullet list enumerates the exact recommendation categories produced (gusset, fillet, thicken_wall, add_base, reorient), which separates it from the sibling apply_design_reinforcements and from analyze_structural_risks.

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?

Usage is implied rather than stated: the reader infers this is the analysis/advice step and that the emitted tool names (e.g. add_mesh_fillet()) are the follow-up action, but the description never explicitly says 'use this before apply_design_reinforcements' or names a when-not condition beyond the units edge case.

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