kernelCAD

Add Feature

add_feature

Idempotent

Use this when you need to insert a new feature line into a script. Insert a new feature line into a kernelCAD script before the last top-level return statement. Returns the modified code as text plus diagnostics from re-evaluating the result. Side-effect-free. Primitives that accept faceLabels (box, cylinder, extrudeRect, extrudeCircle, extrudePolygon, extrudeRoundedRect) can receive opts.faceLabels in the inserted code — use lookup_api to see featureKindFaceLabels for the full value schema.

Input Schema

Name	Required	Description	Default
`code`	Yes	The .kcad.ts source code.
`feature_code`	Yes	Single-statement source line to insert (e.g. `const hole = cylinder(5, 2).translate(10, 10, -1);`).

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 11, 2026

removedOutput schema / properties

Removed value: -{
-  "binding_name": {
-    "description": "JS const name bound to the new construct (when one was created).",
-    "type": "string"
-  },
-  "diagnostics": {
-    "description": "Diagnostics from re-evaluating the modified source.",
-    "items": {
-      "additionalProperties": true,
-      "type": "object"
-    },
-    "type": "array"
-  },
-  "error": {
-    "description": "Failure message (present when ok is false).",
-    "type": "string"
-  },
-  "new_code": {
-    "description": "Modified .kcad.ts source (present on success). Caller persists it.",
-    "type": "string"
-  },
-  "ok": {
-    "description": "Whether the edit applied and re-evaluated cleanly.",
-    "type": "boolean"
-  }
-}

removedOutput schema / required
```
Removed value: -[
-  "ok"
-]
```

Changed1 schema field changedJun 15, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "binding_name": {
+      "description": "JS const name bound to the new construct (when one was created).",
+      "type": "string"
+    },
+    "diagnostics": {
+      "description": "Diagnostics from re-evaluating the modified source.",
+      "items": {
+        "additionalProperties": true,
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "error": {
+      "description": "Failure message (present when ok is false).",
+      "type": "string"
+    },
+    "new_code": {
+      "description": "Modified .kcad.ts source (present on success). Caller persists it.",
+      "type": "string"
+    },
+    "ok": {
+      "description": "Whether the edit applied and re-evaluated cleanly.",
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "ok"
+  ],
+  "type": "object"
+}

First observedMay 25, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Adds real context beyond annotations: it declares the tool is side-effect-free and returns modified code as text plus diagnostics from re-evaluation, which explains what the caller actually gets back. There is mild tension between 'side-effect-free' and readOnlyHint=false, but the surrounding text ('returns the modified code as text') resolves it as a non-writing transform, not a contradiction.

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?

The trigger condition is front-loaded and every sentence carries usable information—insertion location, return content, safety, and the faceLabels pointer. The faceLabels sentence is dense and slightly tacked-on, but it earns its space.

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?

A mutation tool with an output schema, so return values need not be spelled out, yet the description still summarizes them. The main gap is failure behavior: it never says what happens when the script has no top-level return statement or an insertion would be invalid.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema coverage the baseline is 3, but the description adds meaning: feature_code must be a single statement, and inserted code may carry opts.faceLabels for the enumerated primitives, with lookup_api named as the source for the full value schema. That is genuine semantics the schema text does not supply.

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?

Names a specific verb and resource (insert a new feature line) and pins the exact insertion point: before the last top-level return statement in a kernelCAD script. That level of specificity distinguishes it from sibling mutation tools like add_part, add_curve, or remove_feature without opening any schema.

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

Usage Guidelines4/5

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

Opens with an explicit trigger ('Use this when you need to insert a new feature line into a script') and routes the agent to lookup_api for the faceLabels value schema. It does not state when to prefer a sibling instead (e.g., add_pattern_feature, add_constraint, or rewriting via evaluate_script), so it stops short of full alternative routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All kernelCAD tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.