Skip to main content
Glama
Copper

Copper

Render

render
Read-onlyIdempotent

Generate PNG images of schematics, PCB layers, or 3D views so the model can inspect layout after edits and crop in on findings.

Instructions

Look at the design: returns PNG image(s) the model can see. Use after edits to check layout, and with crop to zoom on a finding's at.

target: 'schematic' (every sheet, or sheet='name' for one), 'pcb' (2D layers), 'pcb3d' (raytraced 3D). layers (pcb): default all copper + silkscreen + front mask + outline (no F.Fab: its value texts sit on top of the reference designators); pass e.g. ['F.Cu','Edge.Cuts'] to choose. view: pcb → top|bottom; pcb3d → top|bottom|iso|iso_bottom|front. crop: [x0,y0,x1,y1] in mm document coordinates (schematic / pcb top view). width: pixels, ≤ 2400 (default 1400). Example: render(target='schematic', crop=[90,40,180,110])

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": {
      "target": "<target>"
    },
    "name": "render"
  }
}

Input Schema

NameRequiredDescriptionDefault
cropNo[x0,y0,x1,y1] mm
viewNo
sheetNoschematic sheet name or file stem (default: all sheets, max 8)
widthNo
layersNo
targetYes
projectNoproject path (default: active)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A4.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint/idempotentHint/openWorldHint=false, so the safety profile is covered. The description adds genuinely behavioral detail beyond that: default layer set and why F.Fab is excluded, the 2400px cap with 1400 default width, and the 8-sheet cap. It is solid but not exhaustive; return shape (one image vs many, encoding) is left implicit.

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 purpose and usage, then structured per-parameter with a closing example; almost nothing is waste. The F.Fab parenthetical is longer than needed, but it justifies a non-obvious default, so the cost is minor.

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 7-parameter tool with no output schema, the definition covers target/view interaction, defaults, limits and coordinate spaces, plus a concrete example call. The remaining gap is what exactly comes back for multi-sheet schematics and any size/response constraints, which an agent might want.

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

Parameters5/5

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

With only 43% schema description coverage, the description carries the load and does so well: it explains target values, the per-target valid `view` options, the significance of `layers` with a working example, and that `crop` uses millimetre document coordinates and applies only to schematic/pcb top view. That is meaning the schema alone does not convey.

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 concrete verb and resource ('Look at the design: returns PNG image(s) the model can see') and makes the output medium explicit, which is what separates it from the text-reading siblings like pcb_read/sch_read. An agent knows immediately this is a visual-inspection tool rather than a data query.

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?

'Use after edits to check layout, and with `crop` to zoom on a finding's `at`' gives clear trigger conditions tied to a workflow (verify after mutation, drill into a reported location). The guidance is positive-only — it does not say when to choose this over design_review or verify — so 4 rather than 5.

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