uni-t-uts-mcp

set_ad_frequency

Idempotent

Configures the AD module's center frequency, RF span, resolution bandwidth, and demodulation bandwidth; requires an active AD module and reports any instrument-adjusted values.

Instructions

Configure the AD module's center frequency, RF span, resolution bandwidth and demodulation bandwidth (DBW). AD module must be active. The AM/FM prefix is read fresh from :CONFigure? each call. Ranges come from the programming manual and are not yet live-verified: whether the instrument clamps or errors out of range is UNKNOWN. 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_ad_frequency"
  }
}

Input Schema

Name	Required	Description
`rbw_hz`	No	RF resolution bandwidth in Hz, 100 Hz to 1 MHz (manual; exact step list is 1-1.5-2-3-5-7.5-10, ambiguous in the manual)
`span_hz`	No	RF sweep width in Hz, 100 Hz to 12.8 MHz (manual)
`rbw_auto`	No	Automatic RF resolution bandwidth on/off
`center_hz`	No	Center frequency in Hz, 50 Hz to the instrument's max minus 50 Hz (manual; UNKNOWN to clamp vs error)
`instrument`	No	Which instrument to use (a name from list_instruments). Default: the `default` instrument, or the only one configured
`center_step_hz`	No	Center frequency step in Hz; turns the automatic step off
`center_step_auto`	No	Automatic center frequency step on/off
`demod_bandwidth_hz`	No	Demodulation bandwidth (DBW) in Hz, 400 Hz to 25 MHz (manual; the range text is ambiguous)

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.1.0Nov 13, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations only declare readOnlyHint=false and idempotentHint=true; the description adds substantial context beyond that: the AM/FM prefix is re-read each call, ranges come from a manual and are not live-verified, clamp-vs-error behavior is explicitly UNKNOWN, and requested values are re-read afterward with instrument adjustments surfaced in 'warnings'. It also states the state is left changed with nothing restored. The one missing piece is what happens on failure mid-call (partial application), but the disclosure level is well above the annotation baseline.

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?

Front-loads the operation and its admissibility condition, then layers caveats in a logical order (prefix read, range uncertainty, post-write verification, state persistence). A single dense paragraph with no filler, though the UNKNOWN/ambiguity caveats are stated twice (once in prose, once implicitly via schema) and could be trimmed slightly.

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 an 8-parameter mutation tool with no output schema, the description covers the key unknowns an agent needs: preconditions, uncertainty about out-of-range handling, and the fact that adjustments are reported back via 'warnings'. It does not describe the overall return payload shape (e.g., whether the new settings are echoed), which is the only real gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, including ranges, step lists, and ambiguity notes per parameter, so the schema carries the parameter burden and baseline 3 applies. The description adds only the cross-cutting post-call re-read/warning semantics rather than clarifying any individual parameter.

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?

Names a specific verb (Configure) plus the exact resource and the four settings it controls (center frequency, RF span, RBW, DBW) on the AD module. That scope distinguishes it from siblings like set_frequency, set_bandwidth, and set_ad_filters without needing the schema.

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?

Gives one hard precondition — 'AD module must be active' — which is genuinely useful gating. It never states when to prefer this over set_frequency or set_bandwidth, nor what to do if the module is inactive, so the when/when-not guidance is only implied.

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

Deploy Server