kernelCAD

Evaluate SDF

evaluate_sdf

Read-onlyIdempotent

Use this when you need to sample a signed-distance field at a point. Sample the signed distance from an in-script sdf.* field at a 3D point. Returns { distance, inside, aabb, kind }. Distance is in mm; negative = inside the surface, 0 = exactly on the surface, positive = outside. Use this to verify SDF composition before calling sdf.materialize (which is the expensive step). The script must bind the SdfField via sdf.bind('', field) and pass that name as fieldName. Hint: pass either { file } or { code }, plus { fieldName, point: [x,y,z] }.

Input Schema

Name	Required	Description
`code`	No	Inline kernelCAD script source.
`file`	No	Path to a .kcad.ts script file. Hosted server: cannot read files from your machine — pass `code`, or `project:<slug>` for a saved project.
`point`	Yes	Sample point [x, y, z] in mm.
`fieldName`	Yes	sdf.bind binding name holding the SdfField.

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: -{
-  "aabb": {
-    "additionalProperties": true,
-    "description": "Axis-aligned bounding box of the field (success).",
-    "type": "object"
-  },
-  "distance": {
-    "description": "Signed distance in mm; negative = inside (success).",
-    "type": "number"
-  },
-  "error": {
-    "type": "string"
-  },
-  "errorCode": {
-    "type": "string"
-  },
-  "hint": {
-    "type": "string"
-  },
-  "inside": {
-    "description": "Whether the point is inside the surface (success).",
-    "type": "boolean"
-  },
-  "kind": {
-    "description": "SDF field kind (success).",
-    "type": "string"
-  },
-  "ok": {
-    "type": "boolean"
-  }
-}

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

Changed1 schema field changedSep 28, 2026

changedInput schema / properties / file / description

Previous value: -"Path to a .kcad.ts script file."New value: +"Path to a .kcad.ts script file. Hosted server: cannot read files from your machine — pass `code`, or `project:<slug>` for a saved project."

Changed1 schema field changedJun 15, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "aabb": {
+      "additionalProperties": true,
+      "description": "Axis-aligned bounding box of the field (success).",
+      "type": "object"
+    },
+    "distance": {
+      "description": "Signed distance in mm; negative = inside (success).",
+      "type": "number"
+    },
+    "error": {
+      "type": "string"
+    },
+    "errorCode": {
+      "type": "string"
+    },
+    "hint": {
+      "type": "string"
+    },
+    "inside": {
+      "description": "Whether the point is inside the surface (success).",
+      "type": "boolean"
+    },
+    "kind": {
+      "description": "SDF field kind (success).",
+      "type": "string"
+    },
+    "ok": {
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "ok"
+  ],
+  "type": "object"
+}

First observedMay 25, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint, idempotent, non-destructive), and the description adds genuinely new context: units in mm and the sign convention (negative = inside, 0 = on surface, positive = outside). It restates the return shape '{ distance, inside, aabb, kind }', which the output schema already provides, so it stops just short of full marks.

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?

Front-loaded with the trigger and the core action, then units and sign semantics, then the materialize alternative, then the binding prerequisite. Dense and useful, though the explicit return-shape listing mildly duplicates the output schema.

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

Completeness5/5

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

Complete for a read-only sampling tool: the agent knows when to call it, what to pass (including the file-vs-code choice), the prerequisite binding, the units/sign meaning, and what it is a cheap check for before an expensive operation.

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?

Schema coverage is 100%, so baseline is 3, but the description adds meaning beyond the schema: it explains that fieldName must correspond to a sdf.bind binding and that the caller passes either { file } or { code } plus fieldName and point. That is real invocation guidance the schema alone does not tie together.

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?

States a specific verb (sample the signed distance) and resource (an sdf.* field) at a 3D point, and even names the return payload. An agent can distinguish this from the many add_*/inspect siblings without opening the schema.

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

Usage Guidelines5/5

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

Explicitly conditions use ('use this when you need to sample... at a point') and names the alternative step it precedes: verifying SDF composition before the expensive sdf.materialize. It also states the prerequisite that the script must bind the field via sdf.bind('<name>', field).

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.