Skip to main content
Glama
nk-dho924s-mcp

nk-dho924s-mcp

by bigtimer-dev

scpi

Sends raw oscilloscope commands to a LAN-connected DHO924S, returning query responses while blocking the firmware-crashing measurement query and handling timeouts.

Instructions

Send a raw SCPI command. Commands ending in '?' return the answer. :MEAS:ITEM? is blocked (crashes the firmware's SCPI server). Unsupported queries time out after ~6 s and the connection is re-opened.

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": {
      "command": "<command>"
    },
    "name": "scpi"
  }
}

Input Schema

NameRequiredDescriptionDefault
commandYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses that '?'-suffixed commands return a value, that one specific command crashes the firmware's SCPI server, and that unsupported queries time out after ~6 s with the connection re-opened. What it omits is whether arbitrary commands can mutate instrument state or what permissions/side effects apply, which matters for a raw passthrough tool.

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?

Three tight sentences, front-loaded with the core action and followed by the two operational caveats. No filler and no repetition of the tool name.

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?

An output schema exists, so return values need not be explained, and the single-parameter surface is small. The description covers the critical failure modes, but for a raw-command tool it could note the fallback for the blocked query and whether malformed commands are rejected locally.

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 0% for the single 'command' parameter, so the description must compensate, and it does: it explains that the value is a raw SCPI string and that a trailing '?' changes the response behavior. It stops short of giving syntax conventions (leading colon, separators, case) or a concrete example, which leaves some ambiguity.

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 ("Send a raw SCPI command") and implicitly frames the tool as the low-level escape hatch distinct from structured siblings like measure, acquire, and get_waveform. An agent can tell immediately this is raw passthrough rather than a parsed measurement call.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is implied by "raw" and the warning about the blocked :MEAS:ITEM? command, which functions as a partial when-not. However, it never states when to prefer this over measure or get_waveform, and it does not name an alternative for the blocked query.

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