kernelCAD

Look Up Cookbook

lookup_cookbook

Read-onlyIdempotent

Use this when you need a canonical pattern snippet for a CAD task. Search the kernelCAD cookbook for canonical pattern snippets. Returns top-k snippets matching the natural-language query, ranked by BM25 over title/tags/keywords/trigger. Use when you need a canonical pattern for fillet-after-subtract, non-overlapping booleans, sketch-to-extrude flows, etc. Returns empty if no snippet scores above the relevance floor — proceed without cookbook help in that case.

Input Schema

Name	Required	Description
`k`	No	Max snippets to return. Default 3, max 5.
`id`	No	Exact snippet id as the skills cite it (e.g. "clearance-hole-through-plate"); returns that snippet. An unknown id is ranked as a query.
`query`	No	Natural-language description of what you want to do (e.g. "round the rim of a hole", "build an L-bracket"). One of query / id is required.
`intent`	No	The user's request in one sentence, in the user's own words and language (e.g. 'M4 bracket for a 25 mm tube, print on Bambu A1'). Helps kernelCAD improve; leave out personal data.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 16, 2026

addedInput schema / properties / id

Added value: +{
+  "description": "Exact snippet id as the skills cite it (e.g. \"clearance-hole-through-plate\"); returns that snippet. An unknown id is ranked as a query.",
+  "type": "string"
+}

changedInput schema / properties / query / description

Previous value: -"Natural-language description of what you want to do (e.g. \"round the rim of a hole\", \"build an L-bracket\")."New value: +"Natural-language description of what you want to do (e.g. \"round the rim of a hole\", \"build an L-bracket\"). One of query / id is required."

removedInput schema / required
```
Removed value: -[
-  "query"
-]
```

Changed2 schema fields changedOct 11, 2026

removedOutput schema / properties

Removed value: -{
-  "error": {
-    "type": "string"
-  },
-  "hits": {
-    "description": "Top-k matching cookbook snippets, ranked by BM25.",
-    "items": {
-      "additionalProperties": true,
-      "type": "object"
-    },
-    "type": "array"
-  },
-  "ok": {
-    "type": "boolean"
-  }
-}

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

Changed1 schema field changedOct 3, 2026

addedInput schema / properties / intent

Added value: +{
+  "description": "The user's request in one sentence, in the user's own words and language (e.g. 'M4 bracket for a 25 mm tube, print on Bambu A1'). Helps kernelCAD improve; leave out personal data.",
+  "maxLength": 2000,
+  "type": "string"
+}

Changed1 schema field changedJun 15, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "error": {
+      "type": "string"
+    },
+    "hits": {
+      "description": "Top-k matching cookbook snippets, ranked by BM25.",
+      "items": {
+        "additionalProperties": true,
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "ok": {
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "ok"
+  ],
+  "type": "object"
+}

First observedMay 25, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real behavioral context: BM25 ranking over title/tags/keywords/trigger, a relevance floor, and that empty results mean the agent should proceed without cookbook help.

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 triggering condition and no wasted preamble, but 'canonical pattern snippet' is repeated three times across the passage, which is mildly redundant.

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?

An output schema exists, so return formatting needn't be spelled out; the description still covers ranking, the empty-result case, and when to reach for the tool. Nothing an agent needs to call it correctly is missing.

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% and each parameter (k, id, query, intent) is fully documented in the schema. The description only reinforces 'top-k' and 'natural-language query', adding little beyond the structured fields, so baseline 3 applies.

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?

States a specific verb and resource: search the kernelCAD cookbook for canonical pattern snippets, ranked by BM25. Clear enough to distinguish from execute_cookbook (which runs a snippet) and lookup_api, though it never names those siblings explicitly.

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?

Gives a clear triggering condition ('when you need a canonical pattern snippet for a CAD task') plus concrete examples (fillet-after-subtract, non-overlapping booleans, sketch-to-extrude) and a fallback for empty results. No explicit exclusions or named alternatives, so not a 5.

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

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.