Skip to main content
Glama
FengSui 4G/5G Router MCP Server

FengSui 4G/5G Router MCP Server

Query Signal and Speed History

query_telemetry_history
Read-onlyIdempotent

Retrieve historical download/upload rates, 4G/5G RSRP/SINR, and temperature in time buckets to compare signal or speed before and after band or cell locks.

Instructions

Return the history FengSui keeps of the download and upload rates, the 4G and 5G RSRP and SINR, and the temperature, as time buckets over the last hour, 6, 12 or 24 hours, or a custom window. Use it to see when the signal or speed changed, before and after a band or cell lock for example. Reads FengSui's own records, not the router.

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": "query_telemetry_history"
  }
}

Input Schema

NameRequiredDescriptionDefault
toMsNoEnd of a custom window, as a Unix time in milliseconds (required with preset 'custom').
fromMsNoStart of a custom window, as a Unix time in milliseconds (required with preset 'custom').
presetNoThe window to return, ending now: '1h' (default), '6h', '12h' or '24h'; 'custom' takes fromMs and toMs.
bucketMsNoWidth of each time bucket in milliseconds (optional; chosen from the window when omitted).
maxPointsNoMost buckets to return, 1 to 1440 (default 360).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv1.9.5
    • changedInput schema / properties / bucketMs / description
      Previous value: -"Optional aggregation bucket width in ms."New value: +"Width of each time bucket in milliseconds (optional; chosen from the window when omitted)."
    • changedInput schema / properties / fromMs / description
      Previous value: -"Start Unix timestamp in ms (required when preset === 'custom')."New value: +"Start of a custom window, as a Unix time in milliseconds (required with preset 'custom')."
    • changedInput schema / properties / maxPoints / description
      Previous value: -"Maximum buckets to return (1..1440, default 360)."New value: +"Most buckets to return, 1 to 1440 (default 360)."
    • changedInput schema / properties / preset / description
      Previous value: -"Time window preset (defaults to '1h')."New value: +"The window to return, ending now: '1h' (default), '6h', '12h' or '24h'; 'custom' takes fromMs and toMs."
    • changedInput schema / properties / toMs / description
      Previous value: -"End Unix timestamp in ms (required when preset === 'custom')."New value: +"End of a custom window, as a Unix time in milliseconds (required with preset 'custom')."
  2. First observedv0.1.0

TDQS

A4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description adds genuine value by disclosing data provenance - these are FengSui's stored records, not a live query to the router - which implies possible staleness. It says nothing about retention limits, gaps, or how to interpret the returned buckets.

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 sentences, front-loaded with what is returned, then when to use it, then the provenance caveat. No filler or repetition of schema content.

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?

With no output schema, the description does tell the agent what is returned (which metrics, bucketed, over which windows), which is the essential information. It leaves the exact response shape and behavior under sparsity (e.g. what a bucket with no data looks like) unexplained, a minor gap for a read-only query tool.

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%, so every parameter including preset, fromMs/toMs, bucketMs and maxPoints is already documented with types, defaults and the custom-window dependency. The description only restates the preset windows at a high level and adds no format or interaction detail beyond the schema, so the baseline 3 applies.

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?

Specific verb plus a precisely enumerated resource (download/upload rates, 4G/5G RSRP and SINR, temperature) and the bucketed time-window model. The closing line 'Reads FengSui's own records, not the router' separates it from live-telemetry siblings such as get_cpe_telemetry without needing to open their schemas.

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?

Gives a concrete use case ('see when the signal or speed changed, before and after a band or cell lock'), which tells the agent the scenario that selects this tool. It stops short of naming an alternative tool or stating when not to use it, e.g. when current rather than historical values are wanted.

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