Skip to main content
Glama

import_board

Create a board from a DXF/SVG drawing in one step: largest closed shape becomes outline, circles mounting holes, other shapes keepouts; import KiCad boards as new circuits and report omissions.

Instructions

Set the board from a DXF or SVG drawing as ONE change: the largest closed shape is the outline, circles in it mounting holes, other shapes keepouts. Parts are not moved; the answer lists those now outside. A .kicad_pcb instead makes file a new circuit (outline, parts, nets, copper); the answer lists what did not come over.

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": "<file>",
      "dxf": "<dxf>"
    },
    "name": "import_board"
  }
}

Input Schema

NameRequiredDescriptionDefault
dxfYesA DXF, SVG (sized in mm, in…) or KiCad board in the project folder, e.g. case.dxf or old.kicad_pcb
fileYesCircuit file, e.g. index.circuit.tsx; for a KiCad board, the new one
layerNoDXF: only this layer may make the outline
unitsNoOverrides the drawing's own units
originNo"centre" (default) centres the outline on the origin; "keep" leaves it as drawn
replaceNoReplace the board's holes and keepouts; without it a board that has some is refused

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations, the description carries the full disclosure burden and does a fair job: it states the operation is atomic ('as ONE change'), that parts are not moved, and that the response enumerates parts left outside the new outline or features that failed to transfer. That is genuinely useful state about side effects and return content. It does not cover permission requirements or failure behaviour beyond the refusal implied by the schema's replace flag.

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?

Two dense sentences, front-loaded with the primary action and shape-mapping rules before the KiCad alternative. Nearly every clause carries information, though the capitalized 'ONE change' and the packed parenthetical '(outline, parts, nets, copper)' make it read as compressed notes rather than polished prose.

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?

No output schema exists, so the description must say what comes back, and it does so twice ('the answer lists those now outside', 'the answer lists what did not come over'). Combined with the interpretation rules and the atomicity note, this is close to complete for a six-parameter import tool. Gaps remain around error handling and unit mismatch consequences.

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%, so every parameter including layer, units, origin and replace is already documented, which sets the baseline at 3. The description adds interpretive meaning for the dxf input (how shapes become outline, holes and keepouts) but says nothing extra about layer, units override or origin behaviour. The net contribution beyond the schema is modest.

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 names a specific verb and resource: 'Set the board from a DXF or SVG drawing', and goes further by stating the interpretation rules (largest closed shape = outline, circles = mounting holes, other shapes = keepouts) and the alternate .kicad_pcb import path. That is far more specific than the bare name. It does not, however, distinguish itself from siblings such as import_graphic or import_part, so an agent cannot rule out overlap from the text alone.

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?

It implicitly tells the agent when each input type applies: a drawing sets the board geometry, while a .kicad_pcb creates a new circuit from file. There is no explicit when-not guidance, no mention of prerequisites, and no reference to an alternative tool for cases this one does not cover. Usage is inferable but not spelled out.

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