Copper

Overview Schema Source Related Servers Discussions Admin

Verify (ERC/DRC/review)

verify

Read-onlyIdempotent

Run KiCad ERC, DRC, and design review checks to surface actionable findings, compare new versus fixed issues, and get the exact next tool call before fabrication.

Instructions

Run KiCad's own checks and get actionable findings. Use after EVERY batch of edits (sch_apply, pcb_*), and before fab_export.

what: list of 'erc' (schematic electrical rules), 'drc' (board rules + unrouted nets + schematic↔board parity; zones are refilled in memory, the file is not modified) and 'review' (engineering heuristics, see design_review). Default: ['erc'] plus 'drc' when a board exists. Each finding has severity, type, message, refs (pins like 'U1.3' / footprints), at [x,y] mm (on sheet for sub-sheets) and fix = the exact next tool call, already pointed at the right sub-sheet. Repeats of one problem are merged into one entry with count + all refs. next is the single most useful call to make now; new / fixed compare with the previous run. Checks run on the SAVED files. Example: verify(what=['erc','drc'])

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": "verify"
  }
}

Input Schema

Name	Required	Description
`what`	No
`limit`	No	max finding entries returned per check (default 25)
`parity`	No	check schematic↔board parity in DRC (default true)
`refill`	No	refill zones before DRC (default true)
`project`	No	project path (default: active)

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.1.0Nov 13, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already cover read-only/idempotent/no-open-world, and the description adds real context beyond them: checks run on SAVED files, zones are refilled only in memory and 'the file is not modified', and defaults are ['erc'] plus 'drc' when a board exists. The only nuance is that 'new'/'fixed' compare against a previous run, which is history-dependent, but this is disclosed rather than contradicted.

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 purpose, then usage, then per-mode detail, with an explicit example call at the end. It is dense and information-rich, though the run of sentence fragments in the middle is heavier than strictly needed to select and invoke the tool.

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?

There is no output schema, so the description carries the return-shape burden and does so thoroughly: finding fields (severity, type, message, refs, at [x,y] mm, sheet, fix), repeat merging with count, and the next/new/fixed comparison fields. Nothing an agent needs to call this correctly or interpret results is missing.

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?

Schema coverage is 80%, so the baseline is 3, but the description adds meaning the schema lacks: it explains what each 'what' value actually checks and gives the default behavior for 'what' (not stated in the schema). It does not add anything for 'limit', relying on the schema text for that.

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 ('Run KiCad's own checks and get actionable findings') and immediately enumerates the three check modes 'erc', 'drc' and 'review' with what each covers. It also distinguishes the 'review' mode from the sibling design_review by pointing at it rather than re-describing it.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

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

Explicit timing guidance: 'Use after EVERY batch of edits (sch_apply, pcb_*)' and 'before fab_export', naming the specific siblings that should trigger or precede it. It also routes the agent onward by saying 'next' is the single most useful call to make now.

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