Skip to main content
Glama
ohmstead-mcp

ohmstead-mcp

Official

Create or update Codex part

save_part

Create or update a complete Codex part with terminals, ratings, and block data; pass part_id to revise an existing part and replace its terminal list.

Instructions

Create a Codex part, or update one you own (pass part_id). A part must be complete: name, manufacturer, part number, category, description and at least one terminal (accessory parts, block.kind accessory, need none). Terminal blocks (category terminal) carry block data and per-terminal level/side; terminals can carry load_a / rated_a current data, and protective parts (fuse, breaker) list their allowed trip_ratings. Passive parts (category resistor, capacitor, inductor or diode) with exactly two terminals and no connectors draw on the schematic as inline glyphs, not blocks. Ask the user for datasheet values rather than guessing. On update the terminal list REPLACES the existing one, so include every terminal (use add_part_terminals to just add some). Free users' parts are always public; Pro parts default to private. Pass team (name or id) to create it in that team's Codex (team-only; any editor in the team can edit it later). A part using one of your own signal types in a team needs that signal type in the team too.

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": {
      "name": "<name>",
      "manufacturer": "<manufacturer>",
      "part_number": "<part_number>",
      "category": "<category>",
      "description": "<description>"
    },
    "name": "save_part"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYes
teamNoNew parts: team or class whose Codex it goes in. Ignored on update (a part stays where it is).
blockNo
publicNo
part_idNo
categoryYesOne of: device, plc, psu, battery, relay, terminal, estop, io, hmi, breaker, motor, sensor, resistor, capacitor, inductor, diode
terminalsNo
connectorsNoGender / keying per connector named by the terminals. Omit to keep what's stored.
slot_countNoPLCs: number of I/O module slots
descriptionYes
part_numberYes
manufacturerYesManufacturer name, short code or id (see list_manufacturers)
trip_ratingsNoProtective parts (fuse, breaker): trip ratings in A it can be set to, e.g. [1, 2, 4, 6, 10]. null or [] clears it; omit to keep what's stored.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.2

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the sparse annotations it discloses the highest-risk behavior: on update the terminal list REPLACES the existing one, so omitting terminals silently drops them. It also explains visibility defaults (free users always public, Pro defaults private), team scoping and the requirement that a used signal type must exist in the team. The only tension is that this replacement semantics is not purely additive, while destructiveHint is false, but the description errs on the side of disclosure.

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?

The core create/update distinction is front-loaded and every sentence carries domain information rather than restating the schema. It is a single dense block of roughly 150 words, though, and would scan better split into completeness rules, update semantics, and visibility/team scoping.

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?

For a 13-parameter upsert with no output schema, it covers what an agent must know before calling: the required fields, the at-least-one-terminal rule, the accessory exception, the list-replacement trap, and team/visibility behavior. Return values are not described, but the tool is a save operation and the description does not promise a payload.

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?

With 46% schema coverage over 13 parameters, the description earns credit by explaining the non-obvious ones: part_id as the update switch, team as a name or id that is ignored on update, block data plus per-terminal level/side for terminal blocks, load_a/rated_a as current data, and trip_ratings for protective parts. It leaves the public flag and connectors/slot_count entirely to the schema, so it does not fully compensate for the coverage gap.

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 opening sentence names a specific verb and resource and splits the two modes explicitly: create a Codex part, or update one you own by passing part_id. It also scopes the resource domain (parts in a Codex) in a way no sibling name could be confused with, and immediately states the completeness rule for a valid part.

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 routes the agent away from this tool for the narrow add case ("use add_part_terminals to just add some") and gives a procedural rule for missing data ("Ask the user for datasheet values rather than guessing"). What it lacks is any statement of when NOT to use save_part at all, e.g. for parts you do not own, which is only implied by "one you own".

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