kernelCAD

Export Schematic Netlist

netlist_export

Read-onlyIdempotent

Build the electrical netlist from a schematic — the flat connectivity of every component pin and net, the way KiCad's netlist export works.

Use this to turn a schematic description into machine-readable connectivity: which pins share a net, what each component connects to, and which pins are left unconnected. Feed the result to erc_run for rule checking, or to a BOM/PCB step.

INPUT: schematic — { title?, components: [{ reference, value?, footprint?, libpart?, unit?, dnp?, pins: [{ pin, pinFunction?, pinType?, hiddenPower? }] }], nets: [{ name, netClass?, diffPairPartner?, endpoints: [{ component, pin }] }], noConnects?: [{ component, pin, reason? }] }. Field names follow KiCad's netlist vocabulary (reference, value, footprint, libpart, unit, pin, pinType) so a KiCad .net file maps onto it directly.

OUTPUT: { title?, nets: [{ name, netClass?, endpoints, components, diffPairPartner? }], components: [{ reference, value?, footprint?, libpart?, unit?, dnp?, pinCount, pinNets }], pins: [{ component, pin, net|null, pinFunction?, pinType }], stats: { components, nets, pins, unconnectedPins } }. pinNets maps each pin to its net name, or null when unconnected. Deterministic: the same schematic always yields the same order.

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": {
      "schematic": "<schematic>"
    },
    "name": "netlist_export"
  }
}

Input Schema

Name	Required	Description	Default
`schematic`	Yes

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 7, 2026

TDQS

A3.6/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds determinism ('the same schematic always yields the same order'), which is genuine value, but says nothing about validation failures (unknown component in an endpoint, duplicate reference) or how noConnects interact with the unconnectedPins stat.

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

Conciseness3/5

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

Purpose is front-loaded in the first sentence, but the long INPUT and OUTPUT blocks re-transcribe structure that is already available in the input schema and output schema. With an output schema present, the OUTPUT paragraph is redundant and dilutes the two genuinely additive statements (KiCad vocabulary mapping, determinism).

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 single-parameter, deeply nested tool with an output schema, the definition covers purpose, input vocabulary and downstream consumers well enough to invoke correctly. The remaining gaps are edge-case behavior on malformed input and differentiation from netlist_query.

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?

The reported schema coverage is low, so the description carries weight, and it does add the useful framing that field names follow KiCad's netlist vocabulary so a .net file maps directly. However, the INPUT block largely restates the schema tree rather than explaining semantics the schema lacks, such as the merge behavior of repeated net names or endpoint referential constraints.

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?

The description uses a specific verb+resource ('Build the electrical netlist from a schematic') and immediately defines the resource as 'the flat connectivity of every component pin and net,' which is concrete. It does not distinguish itself from the closely named sibling netlist_query, which is the one plausible confusion an agent would have.

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?

It gives clear downstream routing: 'Feed the result to erc_run for rule checking, or to a BOM/PCB step,' naming a real sibling tool. It does not state when NOT to use it, e.g. versus netlist_query for inspecting an existing netlist, so the boundary is incomplete.

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.