Skip to main content
Glama

native_check

Destructive

Run native ERC, DRC, or full 23-check preproduction validation on a stopped Proteus session, returning real violations from live reports instead of cached or disabled results.

Instructions

Run a stopped-session native check. kind=erc requires a live_read token and a fresh electrical report. kind=drc requires a pcb_read token and refreshes the whole-design ARES physical clearance checker, reading real violations/ignored flags without a dialog. kind=preproduction runs all 23 native PPC checks, including connectivity CRC, on an owned workspace copy with a pcb_read token; restores original selections and closes only its own native PPC dialog. Cached/truncated/partial/disabled results, warnings, skips and ignored violations never count as clean. Current configured rules only, NOT fabrication certification or unrestricted full PCB DRC. Invocation status is separate from passed.

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>"
    },
    "name": "native_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNo
sessionYes
expected_tokenYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

Annotations declare a destructive, non-read-only, closed-world operation, and the description adds real depth: drc refreshes the whole-design ARES clearance checker without a dialog, preproduction works on an owned workspace copy, restores original selections, and closes only its own PPC dialog. It also defines result-trust semantics (cached/truncated/partial/disabled, warnings, skips, ignored violations never count as clean) and separates invocation status from pass. What it does not spell out is the concrete workspace mutation surface, so it reinforces rather than fully explains destructiveness.

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 action, then the three modes, then the trust rules — a logical progression. It is dense to the point of jargon stacking ('including connectivity CRC,' 'ARES physical clearance checker'), but nearly every clause carries actionable constraint rather than repetition.

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

Completeness3/5

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

For a destructive, no-output-schema, zero-coverage-schema tool, the description covers preconditions, per-mode effects, side-effect containment, and what counts as a clean result. It still leaves the shape of the returned data and how the agent should report failure vs. blocked status underspecified, which matters given there is no output schema.

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 all three parameters. It explains the three `kind` enum values in detail and implicitly ties `expected_token` to a live_read/pcb_read token, but it never states which token the caller must supply for each mode versus how `session` is identified or obtained for a stopped session.

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 ('Run a stopped-session native check') and then enumerates the three concrete check modes (erc, drc, preproduction) with what each one actually executes. It also draws explicit boundaries against neighboring concepts ('NOT fabrication certification or unrestricted full PCB DRC'), so an agent can tell this apart from a general DRC or certification tool.

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?

Gives per-mode prerequisites tied to sibling tools: erc needs a live_read token and a fresh electrical report, drc and preproduction need a pcb_read token, and all apply to a stopped session. It states exclusions (not fabrication certification, configured rules only) but never explicitly contrasts with native_verify/native_apply or says when a caller should prefer those.

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