vibe-hardware-mcp

calligraphy_compile_board

Compiles a PCB via Calligraphy EDA and returns DRC telemetry, preview crops, a Stripe Checkout URL, and stablecoin payment instructions for sample or user-supplied boards.

Instructions

Compile a PCB through Calligraphy EDA (3D HDI synthesis + Snowman teardrop pad fillets + Zero-VIPPO DFM surgery + 3D nodal G*V=I physics) and return 0-DRC telemetry, preview crops, a single clickable Stripe Checkout URL, and watch-only per-job USDT/USDC stablecoin payment instructions. Mode A (Zero-File Demo): Pass sample_id='2l_rp2040' (or '2l_stickhub', '4l_carrier'). Mode B (User's Local Board): Pass a local file path in project_path (stdio mode) or pass its contents in pcb_text + filename (or upload_b64 for .PcbDoc/.zip).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "calligraphy_compile_board"
  }
}

Input Schema

Name	Required	Description	Default
`filename`	No		board.kicad_pcb
`pcb_text`	No	Raw CAD file contents (.kicad_pcb, .dsn, .ato, .tsx, .xml) for remote HTTP MCP calls
`sample_id`	No	Optional built-in sample board ID ('2l_rp2040', '2l_stickhub', '4l_carrier')
`upload_b64`	No	Base64-encoded CAD file or .zip bundle for remote HTTP MCP calls
`project_path`	No	Local stdio CLI path or built-in sample ID ('2l_rp2040', '2l_stickhub', '4l_carrier').
`tos_accepted`	No
`requested_sku`	No		route_3d
`rush_delivery`	No
`customer_email`	No		agent@customer.io
`include_eco_pass`	No
`retention_policy`	No		auto_purge_on_download
`no_itar_certified`	No
`export_control_certified`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 10, 2026

TDQS

A3.5/5.0

Behavior3/5

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

With no annotations, the description carries the full burden. It does disclose major side effects: a billable SKU, a created Stripe Checkout URL, and per-job stablecoin payment instructions. But it says nothing about cost implications of requested_sku, what retention_policy actually does to uploaded files, or what the export-control/ITAR flags gate, which are the behaviors an agent most needs before invoking.

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?

Front-loaded and the mode split is clearly structured, but the first sentence is an overloaded run-on stuffed with brand jargon that costs the reader more than it conveys. Roughly half the parenthetical tokens add no decision-relevant information.

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

Completeness3/5

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

For a 13-parameter tool with no output schema and no annotations, the description covers input modes and return artifacts adequately but omits the semantics of the commercial and compliance flags. An agent could invoke it, but would be guessing about SKU selection, retention, and certification defaults.

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 coverage is only 31%, so the description should compensate. It explains the file-input trio (project_path, pcb_text+filename, upload_b64) and sample_id values, but leaves 8 parameters (requested_sku, rush_delivery, customer_email, include_eco_pass, retention_policy, tos_accepted, no_itar_certified, export_control_certified) undocumented in both schema and prose; the enum SKU tiers are not described at all.

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?

Opens with a specific verb+resource ('Compile a PCB through Calligraphy EDA') and enumerates the concrete artifacts returned (0-DRC telemetry, preview crops, Stripe Checkout URL, payment instructions). The long parenthetical of marketing jargon ('Zero-VIPPO DFM surgery', '3D nodal G*V=I physics') dilutes rather than sharpens the purpose, and it never contrasts itself with siblings like calligraphy_route_pcb or calligraphy_preflight_audit.

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?

The Mode A / Mode B split is genuinely useful routing guidance, including which parameter to use per mode and which transport (stdio vs HTTP) each implies. It stops short of saying when NOT to use this tool or when a sibling (preflight_audit, route_pcb, create_coinbase_checkout) is the better first call.

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

Deploy Server