Skip to main content
Glama
ohmstead-mcp

ohmstead-mcp

Official

Update harness

update_harness

Override how loose wires between subsystems are grouped and drawn: retag or rename a harness, set trunk/wire display, adjust minimum wire counts, or promote it to a cable.

Instructions

Overrides for a harness: all loose wires between the same two subsystems (or a subsystem and a terminal strip), worked out automatically and drawn as one trunk with a tag (H1, H2…). get_project lists them. Retag, name it, draw it as a trunk or as separate wires, everywhere or in one view, or change its minimum wire count. null clears a field back to automatic. The project-wide minimum is update_project harness_min.

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": {
      "project_id": "<project_id>",
      "harness": "<harness>"
    },
    "name": "update_harness"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNo
showNoTrunk or separate wires, in every view.
specNoWith promote: printed on the cable, e.g. "12×0.75 PUR".
viewNoWith view_show: a subsystem name or id to set it for, or null for the top level.
harnessYesHarness tag (H1) or key from get_project
new_tagNo
promoteNoThe harness really is one multi-core cable: its wires become conductors of a new W-tagged cable landing on their terminals. Edit it with update_cable; remove_cable puts the wires back.
min_wiresNoFewest wires for this pair to count as a harness.
view_showNoTrunk or separate wires in that view; null goes back to `show`.
project_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.2

TDQS

A3.8/5.0
Behavior4/5

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

Annotations only establish that this is a non-read-only, non-destructive, closed-world mutation, so the description adds real value: 'null clears a field back to automatic' explains reset semantics that the schema states only for show/view_show. It also explains that the min_wires value is a threshold for when a pair counts as a harness, which is behavior an agent could otherwise misread as an exact wire count; it does not cover partial-update semantics or what happens to references on retag.

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?

There is no filler, but the text is telegraphic: sentence fragments, a mid-paragraph 'get_project lists them' aside, and an 'or…or…' list that forces re-parsing. Front-loading is weak because the actual operations trail a conceptual definition of a harness.

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 10-parameter mutation with no output schema, the definition covers the concept, discovery route, and reset semantics, but leaves open whether omitted fields are left unchanged, what a retag does to existing references, and what the response contains. Adequate to call correctly, not complete enough to predict results.

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 70%, and the prose maps most parameters to intent: retag (new_tag), name it, draw as trunk or separate wires (show), everywhere or in one view (view/view_show), and minimum wire count (min_wires). The promote/spec path to a W-tagged cable is left entirely to the schema, but that documentation is thorough, so the gap is minor.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description defines the resource precisely (bundled loose wires between two subsystems drawn as one H-tagged trunk) and enumerates the operations: retag, rename, switch trunk/wires display, and change min wire count. It never states the verb plainly up front — the first sentence is a definition of a harness rather than of the tool — but the following sentence makes the effect on the resource unambiguous.

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 to siblings in two concrete places: 'get_project lists them' for discovering the harness identifier, and 'The project-wide minimum is update_project harness_min' to redirect the global setting away from this per-pair tool. It stops short of saying when this tool should not be used or what prerequisite state is needed.

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