Skip to main content
Glama

Running Cat Geo

River levels

river_gauges
Read-only

River levels from official gauges (Germany, France, England, Scotland, the Netherlands, Flanders, Luxembourg, Czechia, Ireland, Switzerland, Sweden, Finland, Canada, USA, and in Spain Catalonia and the Guadalquivir basin, in Italy Lombardy, Veneto, Emilia-Romagna and South Tyrol). Three modes, picked by the arguments in this order: gaugeId gives the history of that gauge over days days (its id comes from the other two modes); else bbox gives every gauge in the box, up to 200, and lon, lat and radiusKm are ignored; else lon and lat give up to 20 gauges within radiusKm, nearest first. Each gauge has its id, river and station name, [lon, lat], the latest level in cm, discharge in m³/s where measured, the change over a day and the warning state where the agency publishes one. Counts as one request.

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": "river_gauges"
  }
}

Input Schema

NameRequiredDescriptionDefault
latNoLatitude of the point to search around (with lon)
lonNoLongitude of the point to search around (with lat)
bboxNo[west, south, east, north], up to 16 square degrees, instead of lon and lat
daysNoDays of history, with gaugeId only
gaugeIdNoA gauge id such as hubeau:V000201201, for its history
radiusKmNoSearch radius in km around lon and lat, 25 by default; not used with bbox or gaugeId

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the readOnlyHint and openWorldHint annotations, the description discloses result caps (200 for bbox, 20 for point search), that lon/lat/radiusKm are silently ignored in bbox mode, the default radius of 25 km, the geographic coverage of the federated sources, and a cost note ("Counts as one request"). That is substantive behavioral context an agent cannot get from annotations alone.

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?

A single dense paragraph with no filler sentences, and the mode logic is stated compactly and in evaluation order. The long parenthetical roll-call of regions occupies front-loaded space that is lower value than the mode rules, slightly diluting structure.

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?

There is no output schema, and the description compensates by enumerating the returned fields per gauge including units. Combined with mode behavior, caps, and coverage, nothing an agent needs to invoke this correctly 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%, so the baseline is 3, but the description adds cross-parameter meaning the schema cannot express: the precedence order between gaugeId, bbox, and lon/lat, and the fact that radiusKm and the point coordinates are dropped when bbox is supplied. It also clarifies where a gaugeId originates (the other two modes).

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 names the specific resource (official river gauge levels) and enumerates exactly what each result contains: id, river/station name, coordinates, level in cm, discharge, daily change, and warning state. It also spells out the three retrieval modes, so an agent can tell precisely what the tool does before opening 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 Guidelines4/5

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

Mode selection is stated explicitly and with precedence: gaugeId for history, else bbox for all gauges in a box, else lon/lat for the nearest within radiusKm. What is missing is guidance against sibling tools such as point_report or weather_forecast, but the internal when-to-use rules are unusually clear.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources