Skip to main content
Glama

run_pcb_drc

Read-onlyIdempotent

Execute rigorous physical Design Rule Check (DRC) on a routed PCB and return a scored violation report. Verifies what the router cannot: true copper-to-copper clearance between different nets (segment-to-segment geometry, not grid cells)…

Instructions

Execute rigorous physical Design Rule Check (DRC) on a routed PCB and return a scored violation report. Verifies what the router cannot: true copper-to-copper clearance between different nets (segment-to-segment geometry, not grid cells), acid traps and sub-90-degree etching crevices (IPC-2221B 10.1.2), trace width vs process capability, board-edge and mounting-hole keepout intrusion, RF antenna keepout, and high-speed differential pair skew (IPC-2141A 3.4). Returns severity-tagged violations with measured vs required values plus a 0-100 score; passed is false when any blocking error remains.

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": {
      "modules": "<modules>",
      "netlist": "<netlist>"
    },
    "name": "run_pcb_drc"
  }
}

Input Schema

NameRequiredDescriptionDefault
modulesYesComponent modules dict (from synthesize_circuit output).
netlistYesNetlist dict with 'connections' (from synthesize_circuit output).
ses_textNoSpecctra SES session text to check. When omitted the board is routed first with the default exact engine, so the report describes what would actually be fabricated.
board_width_mmNoPCB width in mm (default: 70.0).
board_height_mmNoPCB height in mm (default: 50.0).
check_acid_trapsNoWhether to check acute-angle etching traps and 90-degree high-speed corners (default: true).
max_diff_skew_mmNoMaximum allowed USB differential pair length mismatch in mm (default: 1.250).
min_clearance_mmNoMinimum copper-to-copper clearance in mm (default: 0.100 / 4mil).
edge_clearance_mmNoMinimum copper-to-board-edge setback in mm (default: 0.800).
min_trace_width_mmNoMinimum manufacturable trace width in mm (default: 0.127 / 5mil).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.16.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, yet the description still adds real value: severity-tagged violations with measured vs required values, a 0-100 score, and the rule that `passed` is false only when a blocking error remains. It does not describe cost/runtime or how many violations are returned, which keeps it from a 5.

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 sentences, front-loaded with the action and result, followed by a dense but purposeful enumeration of checks and the return contract. The IPC standard citations (IPC-2221B 10.1.2, IPC-2141A 3.4) are mildly verbose but justify the rigor claim, so little is wasted.

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 10-parameter tool with nested objects, the description explains what is checked and what comes back (violation list with severity and measured/required values, plus a score and a passed flag), which compensates for the absent output schema. It stops short of stating the data dependency on synthesize_circuit output, which is only carried by the parameter descriptions.

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 one of the 10 parameters is already documented, including the important ses_text fallback behavior and all threshold defaults. The description only implies which parameters exist by naming the corresponding checks (acid traps, skew, clearance, trace width); it adds no extra syntax or interaction guidance beyond the schema. Baseline 3 is appropriate.

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 specific verb + resource ("Execute rigorous physical Design Rule Check (DRC) on a routed PCB") and enumerates the exact checks performed, including clearances, acid traps, trace width, keepouts and diff-pair skew. The phrase "verifies what the router cannot" implicitly separates it from autoroute_pcb, and "physical" separates it from electrical checks like run_erc/validate_netlist in the sibling list.

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?

Usage is implied (post-routing, pre-fabrication verification) rather than stated. There is no explicit "use this instead of calculate_ipc2221_clearance / calculate_differential_skew" routing, and no precondition like "requires a completed routing session or synthesize_circuit output." An agent can infer the context but must reason about it.

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

Deploy Server

Other Tools