Skip to main content
Glama

audit_find_pin_net_name_mismatches

Detect IC pins named like power or ground pins that connect to non-power or non-ground nets, flagging swapped rails and broken reference planes.

Instructions

Find IC pins whose NAME looks like a power / ground pin but whose connected NET is not actually a power / ground rail.

Examples flagged:

  • pin "VCC" wired to a non-power net (swapped rail bug)

  • pin "GND" or "VSS" wired to a non-ground net (broken reference plane) ERC won't catch these: the wire is connected, the names just disagree on intent. A class of bug that ships when the user copied a sub-circuit and forgot to re-tag the rail.

Pattern: ports the dashboard's JS-side analyzePinNetMismatch as an authoritative MCP audit.

Returns: Dict with {checked, violations, items[]} where each item carries {designator, mismatches[]} with one entry per offending pin: {pin, name, net, kind}. kind is power_pin_on_non_power_net or ground_pin_on_non_ground_net.

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": "audit_find_pin_net_name_mismatches"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.1

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the full load and does most of it: it discloses the detection logic, the fact that connectivity is already valid (only intent mismatches), the exact result payload, and the two enumerated `kind` values. The remaining gap is scope — it never says whether it scans the active sheet, the whole project, or requires a recompile beforehand.

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 the one-sentence definition, then examples, then rationale, then return shape — a sensible order. The "Pattern: ports the dashboard's JS-side analyzePinNetMismatch" line is internal implementation trivia that adds little for an agent choosing or calling the tool.

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 zero-parameter audit with an output schema, the description is nearly sufficient: it explains the check, the failure rationale, and even restates the return structure. The one thing an agent still cannot infer is the scan scope and any prerequisite (e.g. compiled/fresh design state).

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

Parameters4/5

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

The tool takes zero parameters, so there is nothing to disambiguate; the schema is an empty object at 100% coverage. Baseline 4 applies, and no parameter-level meaning is missing.

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 precise verb and object: find IC pins whose name implies power/ground but whose net does not. Concrete examples ("VCC" on a non-power net, "GND"/"VSS" on a non-ground net) remove any ambiguity and distinguish it from generic ERC tools 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 Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It establishes the usage context well by explaining the bug class (copied sub-circuit with an un-retagged rail) and explicitly says "ERC won't catch these", which routes the agent away from proj_run_erc for this case. It stops short of naming the nearest audit_* siblings (e.g. audit_find_orphan_power_objects, audit_find_unconnected_ic_pins) as alternatives, so it is clear but not fully disambiguated.

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