Skip to main content
Glama

audit_find_bad_connections

Detect dangling PCB track and arc endpoints that are near same-net primitives but not touching, revealing hidden open connections before fabrication.

Instructions

Find PCB tracks / arcs with endpoints that are close to another same-net primitive but don't actually touch.

Walks every track / arc on a signal layer. For each endpoint, looks for ANOTHER same-net primitive (track / arc / pad / via) within tolerance_mils. If nothing same-net is in range, the endpoint is "dangling": Altium may show it as connected in the analyser (centre-point heuristic) but the photoplot will not bridge it, producing a real open on the fab side.

Visual review misses these because at 100% zoom the gap is invisible; DRC sometimes catches them under a "Clearance" or "Modified Polygon" rule but not reliably.

Skipped: teardrops (intentionally offset), primitives inside components (they ride the pad), primitives without a net, full circle arcs (no anchor endpoint).

Args: tolerance_mils: Coord tolerance in mils. 0 = exact match required (rare, since router can place tracks on sub-mil grid). Defaults to 1 mil; bump to 5 or 10 to surface gross misalignments only.

Returns: Dict with: - checked: track + arc primitives inspected - violations: primitives with at least one dangling endpoint - tolerance_mils: echo of the tolerance used - items: per-violation {kind, layer, net, at} where at is the dangling endpoint's "(x,y)" in mils

Input Schema

NameRequiredDescriptionDefault
tolerance_milsNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.1

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses scope (walks every track/arc on signal layers), exclusions (teardrops, in-component primitives, netless primitives, full-circle arcs), and the analyser-vs-photoplot discrepancy. It does not mention runtime cost or that it is read-only, but the audit premise implies no mutation.

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 a precise one-sentence definition, then algorithm, rationale, exclusions, args and returns. The paragraph on visual review and DRC is slightly verbose but does earn its place by justifying the tool's existence.

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

Completeness5/5

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

Output schema exists, yet the description still explains checked/violations/tolerance/items fields, and covers algorithm, exclusions and parameter tuning. An agent has everything needed to call and interpret it.

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?

Schema description coverage is 0%, so the description must compensate, and it does: defines tolerance_mils as centre tolerance in mils, explains 0 means exact match (rare due to sub-mil grid), notes the default of 1 mil, and advises 5-10 for gross misalignments.

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?

First sentence names the exact resource (PCB tracks/arcs with endpoints near a same-net primitive but not touching) and the failure mode it detects. It is clearly distinct from sibling audits such as pcb_audit_pad_center_connected or audit_find_unconnected_ic_pins.

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?

Explains the situation where the tool is warranted (gaps invisible at 100% zoom, DRC unreliable) and gives concrete guidance to bump tolerance to 5 or 10 for gross misalignment. It does not explicitly name which sibling to use instead of or alongside this one, so it stops short of full routing guidance.

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