Skip to main content
Glama
ohmstead-mcp

ohmstead-mcp

Official

Import a design (wire list, BOM, or a drawing you read)

import_wiring_list

Bring existing EPLAN, SKYCAD, AutoCAD Electrical, or SolidWorks Electrical wiring and BOM data into a new Ohmstead project, then preview proposed devices, parts, and subsystems before applying.

Instructions

Import an existing design into a NEW Ohmstead project. Sources: rows you extracted yourself (read an EPLAN / SKYCAD / AutoCAD Electrical / SolidWorks Electrical PDF page by page: devices with tags + part numbers from the parts list, wires as TAG:TERMINAL pairs from the cross-references / wire numbers, strips with their terminal order from the terminal diagrams), and/or CSV text: wire_csv (connection / wire list export) and bom_csv (BOM / parts list). Devices are matched to the Codex by part number; unknown part numbers are PROPOSED, never created unless listed in accept_parts. BOM lines no wire touches and no Codex part matches (enclosure, hardware) are listed, not placed. Strip numbers are imported locked. level: as-drawn (strips exactly as imported), light (pack, numbers kept), split-pack (split by subsystem + function, pack, numbers kept), full (split, pack, renumber). Device connections are checked to stay identical. Devices with no subsystem hint get PROPOSED subsystems from strip function and how they connect (Power, Control, field groups, areas from numbered tags), never applied unless listed in accept_subsystems; to change one, set subsystem on those device rows and run the dry run again. apply=false (default) returns the report only; show it to the user and ask before applying.

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": {
      "title": "<title>"
    },
    "name": "import_wiring_list"
  }
}

Input Schema

NameRequiredDescriptionDefault
teamNoTeam or class name or id to create the project in. Omit for your personal workspace.
applyNo
levelNoas-drawn
titleYes
wiresNo
sourceNoother
stripsNoTerminal order per strip from terminal diagrams
bom_csvNoBOM / parts list CSV text (tag, part number, manufacturer, description, section)
devicesNo
wire_csvNoWire / connection list CSV text (EPLAN, AutoCAD Electrical, SolidWorks Electrical exports; columns found by name)
column_mapNoOverride column names, e.g. {"fromTag": "Start device", "partNumber": "Order no"}
accept_partsNoProposed part numbers to create in the user's Codex before importing (["all"] for every proposal whose manufacturer exists)
accept_subsystemsNoProposed subsystem names to apply (["all"] for every one). Devices left out stay at project level.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.2

TDQS

A4.4/5.0
Behavior5/5

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

Annotations only declare it is a non-read-only, non-destructive, closed-world write, but the description adds rich context: unknown part numbers are PROPOSED never created, unmatched BOM lines (enclosure, hardware) are listed not placed, strip numbers are imported locked, device connections are verified identical, and the default is a dry run. That is far beyond what the annotations convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The content is valuable but delivered as one dense paragraph with long parenthetical enumerations (EPLAN/SKYCAD/AutoCAD/SolidWorks lists, nested rules). It is front-loaded well by the first sentence, but the middle sentences would be far more scannable as bullets and several clauses could be trimmed.

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 13-parameter, deeply nested mutation tool with no output schema, the description covers sources, matching behavior, level semantics, proposal/accept gating, and the dry-run contract. It leaves out only column_map and the shape of the returned report, which are minor relative to the overall coverage.

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 54% across 13 params, so the description must compensate and largely does: it defines all four level enum values, explains accept_parts (including the 'all' sentinel) and accept_subsystems, and describes the three input source shapes. It omits column_map and the team parameter, leaving those to the schema.

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?

The description opens with a specific verb and resource ('Import an existing design into a NEW Ohmstead project') and then enumerates exactly which sources are accepted (extracted PDF rows, wire_csv, bom_csv). An agent can tell this is the bulk-design-ingest tool and distinguish it from single-item siblings like add_connections or create_project.

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 gives a clear operating workflow: apply=false (default) returns a report only, show it to the user and ask before applying, and it explains how to correct proposed subsystems by re-running the dry run. It does not explicitly compare against alternatives such as import_project_file, so it stops short of a full when/when-not routing statement.

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