uni-t-uts-mcp

set_emi_measurement

Idempotent

Configure EMI measurement settings such as standard, sweep sequence, detectors, dwell time, averaging, and search counts on the analyzer; the EMI module must already be active.

Instructions

Configure the EMI module's measurement: standard (none/cispr), sweep sequence and re-measure mode, trace/meter/final detectors, meter dwell time, averaging, and search mode/counts. EMI module must be active (select_instrument_module). At most two of quasi_peak/average_continuous/average may be selected together per detector group (the manual documents this as mutually exclusive). Everything requested is re-read afterwards and any instrument-adjusted value is reported in 'warnings'. Leaves the new state (nothing is restored).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "set_emi_measurement"
  }
}

Input Schema

Name	Required	Description
`sequence`	No	Sweep sequence: scan only, search only, scan+search+measure, scan+search, search+measure, measure only
`standard`	No	NONE allows 1-3-10 RBW steps 1 kHz-3 MHz; CISPr fixes RBW to 200 Hz/9 kHz/120 kHz/1 MHz and filter type to EMI (6 dB)
`remeasure`	No	What the measure step covers
`instrument`	No	Which instrument to use (a name from list_instruments). Default: the `default` instrument, or the only one configured
`peak_count`	No	Search peak count, 1 to 50
`search_mode`	No	Peak-search mode for the signal table
`average_type`	No	Averaging type
`average_count`	No	Average count, 1 to 999
`meter_dwell_s`	No	Meter detector dwell time in seconds, 0.001 to 100 (one value for all meters)
`segment_count`	No	Search segment count, 1 to 50
`final_detectors`	No	Final-measurement detector edits
`meter_detectors`	No	Per-meter detector (meter index 1 to 3)
`trace_detectors`	No	Per-trace detector (trace index 1 to 3)

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.1.0Nov 13, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Goes well beyond the annotations (readOnlyHint=false, idempotentHint=true) by disclosing that all requested values are re-read afterwards and any instrument-adjusted value comes back in 'warnings', and that the tool is non-transactional ("Leaves the new state (nothing is restored)"). It also surfaces a real selection constraint (at most two of quasi_peak/average_continuous/average per detector group). What it does not cover is failure behavior — e.g. what happens if the EMI module is not active, or how partial application is reported, even though those semantics are otherwise consistent with the idempotent, mutating annotation.

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?

Two dense sentences, front-loaded with the covered settings before the precondition and the caveats. Nothing is padding, though the very long first sentence compresses many distinct settings into one clause chain and would read faster as a short list.

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, all-optional mutation tool with no output schema, the definition covers the precondition, the post-write verification/warnings channel, non-restoration, and a key cross-parameter constraint. The remaining gap is error/partial-failure behavior if the module is inactive or an instrument rejects a value.

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 description coverage is 100%, so the baseline is 3; the description earns above that by adding semantics the schema cannot express — the per-detector-group exclusivity rule for quasi_peak/average_continuous/average, and the interaction between standard and the detector/limit groupings. It still does not clarify how the array-indexed trace/meter/final detector entries interact when the same index is edited twice.

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 ("Configure the EMI module's measurement") and then enumerates exactly which settings are covered: standard, sweep sequence, re-measure mode, trace/meter/final detectors, dwell time, averaging, search mode/counts. That enumeration lets an agent separate it from siblings like set_emi_correction, set_emi_limit_line or set_emi_scan_table 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 Guidelines4/5

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

It states a hard precondition ("EMI module must be active (select_instrument_module)") and names the sibling that establishes that state, which is genuine routing guidance. It does not say when to prefer this over adjacent configuration tools such as configure_measurement or set_detector, so it stops short of explicit alternatives/exclusions.

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

Deploy Server