Skip to main content
Glama
fieldpuppet

fieldpuppet

Official

Add a point to a device

add_point

Add a named Modbus point to a running simulated device without restarting it or disturbing connected clients. Set its initial value or signal immediately.

Instructions

Add one new named point (a coil, discrete input or register value) to a device that is already running, without restarting it or disturbing connected clients. Use it to extend a template device; to define points when a device is first created, pass them to create_device instead. The point takes its initial value, or starts its signal, immediately. Returns the new point with its current value. Fails if the device does not exist, the name is already used on that device, or the definition is invalid (for example a 32-bit type in a bit table).

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": {
      "device_id": "<device_id>",
      "point": "<point>"
    },
    "name": "add_point"
  }
}

Input Schema

NameRequiredDescriptionDefault
pointYesDefinition of one point: a named value stored at a Modbus address.
device_idYesId of a running device, as returned by create_device, clone_device or list_devices.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv0.1.2
    • changedInput schema / properties / device_id / description
      Previous value: -"Device id as returned by create_device or list_devices."New value: +"Id of a running device, as returned by create_device, clone_device or list_devices."
    • addedInput schema / properties / point / description
      Added value: +"Definition of one point: a named value stored at a Modbus address."
    • changedInput schema / properties / point / properties / address / description
      Previous value: -"Zero-based protocol address."New value: +"Zero-based protocol address (holding register 40001 is address 0)."
    • addedInput schema / properties / point / properties / description / description
      Added value: +"Free text describing the point. Informational only."
    • addedInput schema / properties / point / properties / name / description
      Added value: +"Point name, unique within the device. Used by set_point, set_signal and read_points."
    • addedInput schema / properties / point / properties / table / description
      Added value: +"Modbus table: coil and discrete hold bits, holding and input hold 16-bit registers."
    • addedInput schema / properties / point / properties / unit / description
      Added value: +"Engineering unit shown next to the value, for example kW or bar. Informational only."
  2. First observedv0.1.1

TDQS

A4.9/5.0
Behavior5/5

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

Annotations only say readOnly=false, idempotent=false, destructive=false; the description goes much further by disclosing that no restart occurs, connected clients are undisturbed, the initial value/signal takes effect immediately, the new point is returned with its current value, and three concrete failure modes (missing device, duplicate name, invalid definition such as a 32-bit type in a bit table). This is exactly the mutation-side context annotations cannot carry.

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

Conciseness5/5

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

Action and its key property (no restart, no client disruption) are front-loaded, then the sibling routing, then the return value and failure list. Every sentence carries distinct information; nothing is redundant with the title or schema.

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?

With no output schema, the description compensates by stating what is returned, and for a two-parameter mutation on a running device it covers preconditions, side effects, error conditions, and the creation-time alternative. Nothing material 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 100% and the nested point schema documents every field including the signal object variants, so the description rightly does not repeat them. It does add a small gloss on what the point represents ('a coil, discrete input or register value') that helps orient the agent before it reads the enum.

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 ('Add one new named point... to a device that is already running') and immediately differentiates the operation from create_device. An agent can distinguish it from siblings like set_point or create_device without opening any schema.

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?

Explicitly names the alternative and the condition that selects it: 'to define points when a device is first created, pass them to create_device instead.' The phrase 'Use it to extend a template device' gives the positive case too, so both branches are covered.

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