Skip to main content
Glama

pcb_route_layers

Destructive

Routes between real through-hole pads across TOP/BOT layers using calibrated through-vias, with A* or explicit waypoints, while preserving existing copper and verifying native via geometry.

Instructions

Route between real through-hole pads across TOP/BOT with full-diameter calibrated through-vias. Requires fresh pcb_read token and native via_style. Automatic layer-state A* or explicit waypoints of {layer,position_nm}; a layer change repeats the same position. Preserves all old wires/vias and verifies exact native copper, style, hole, span and multiplicity. Only two-copper-layer rectangular boards with known geometry. NOT push/shove, blind/buried vias, full DRC or atomic. Save/reopen for disk verification.

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": {
      "session": "<session>",
      "expected_token": "<expected_token>",
      "net": "<net>",
      "from_pad": "<from_pad>",
      "to_pad": "<to_pad>"
    },
    "name": "pcb_route_layers"
  }
}

Input Schema

NameRequiredDescriptionDefault
netYes
to_padYes
grid_nmNo
sessionYes
from_padYes
max_viasNo
width_nmNo
end_layerNo
via_styleNo
waypointsNo
start_layerNo
clearance_nmNo
expected_tokenYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior5/5

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

Goes well beyond the annotations (readOnly=false, destructive=true, closed-world): it discloses that old wires/vias are preserved, that exact copper/style/hole/span/multiplicity are verified, that the operation is non-atomic, and that a save/reopen is needed for disk verification. The fresh-token auth requirement and A* vs explicit-waypoint modes are additional behavioral context an agent could not obtain from structured fields.

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?

Purpose is front-loaded in the first sentence, followed by prerequisites, modes, guarantees, constraints, exclusions and verification advice. Dense but every sentence carries load; the telegraphic style is slightly terse but never padded.

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 complex 13-parameter, no-output-schema, mutation tool, the description covers purpose, prerequisites, algorithm modes, preserved state, verification, board constraints and explicit non-guarantees. It stops short of describing the numeric tuning parameters or return/verification output, but is otherwise appropriately complete.

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 0%, so the description must carry parameter meaning, and it does explain the waypoint object shape ({layer, position_nm}), the layer-change-repeats-position rule, via_style as native, and the token freshness. However, many of the 13 parameters (grid_nm, max_vias, width_nm, clearance_nm, session, net/from_pad/to_pad) get no semantic coverage, leaving a real gap.

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 and resource: route between real through-hole pads across TOP/BOT with full-diameter calibrated through-vias. The scope is precise enough to distinguish it from the push/shove routing siblings, which it explicitly excludes.

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?

Provides a prerequisite (fresh pcb_read token, native via_style), scope constraints (only two-copper-layer rectangular boards with known geometry), and clear exclusions (NOT push/shove, blind/buried vias, full DRC, atomic). Alternatives are implied via 'NOT push/shove' rather than named as tools, so routing to a specific sibling is left slightly implicit.

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