German and Swiss river gauges, groundwater and flood levels from ten official sources
Scored across 6 tools
Each tool targets a distinct facet: aggregate flood status, future forecast, historical readings, single-station metadata, weather, and station search. The search_stations vs get_station and get_readings vs get_forecast boundaries are clear from the descriptions.
All six tools follow a consistent snake_case verb_noun pattern (get_* and search_*), with no mixing of conventions or vague verbs.
Six tools is well-scoped for a hydrological data server; each covers a distinct, non-redundant capability without bloat.
The set covers search, metadata, time-series readings, forecasts, flood status, and weather, forming a coherent workflow. Minor gaps exist around listing/aggregating available stations or regions, but core use cases are supported.
Current flood situation: stations with an active LHP flood class (1 small … 4 very large), optionally per federal state.
| Name | Required | Description | Default |
|---|---|---|---|
| federalState | No | ISO 3166-2 code, e.g. DE-BY |
| Name | Required | Description |
|---|---|---|
| stations | Yes | |
| countByClass | Yes | Station count per flood class name |
| stationsWithFlood | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, openWorld and non-destructive behavior, so the safety profile is covered. The description adds genuine domain behavior beyond the annotations: only stations with an active flood class are returned, and the 1–4 class scale is defined. It stops short of describing result volume or ordering.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single compact sentence with the core purpose front-loaded and the optional filter trailing. No filler, and the parenthetical class scale earns its space by defining the key domain concept.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With an output schema present, return values need no explanation, and the optional parameter is covered. The only gap is that the acronym 'LHP' is left unexplained and it is not stated what an unfiltered call returns, though both are minor for a scope-sensitive read tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the single optional parameter is fully documented in the schema (ISO 3166-2 code). The description only restates that state filtering is optional, adding no syntax or edge-case detail beyond the schema, so the baseline of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific resource (current flood situation) and scope (stations with an active LHP flood class), which is concrete enough for an agent to act on. It implicitly contrasts with the forecast sibling by emphasizing 'current', but it does not explicitly differentiate itself from get_forecast, get_readings, or search_stations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
'Current' and 'optionally per federal state' imply when this tool is appropriate (real-time status, optional regional narrowing), but there is no explicit statement of when to prefer it over get_forecast or get_readings, nor any exclusion or prerequisite.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Newest published water-level forecast for a station: the median of the state agency model run, future points within the horizon. Only gauges whose state publishes numeric forecasts have one, so an empty result is normal. Indicative, not an official warning.
| Name | Required | Description | Default |
|---|---|---|---|
| stationId | Yes | Namespaced station id, e.g. "lhp:RP_2640010" | |
| horizonHours | No | Hours ahead, default 72, capped at 240 |
| Name | Required | Description |
|---|---|---|
| note | Yes | |
| unit | Yes | |
| count | Yes | |
| points | Yes | |
| source | Yes | |
| stationId | Yes | |
| generatedAt | Yes | Model run time; null when none was published |
| horizonHours | Yes | |
| valueDivisor | Yes | Divide valueCentimeters by this to read it in `unit` |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the safe-read profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint). The description adds real behavioral value beyond them: data provenance (median of the state agency model run), the expected-empty-result condition, and the non-authoritative disclaimer. It stops short of describing pagination or cadence of publication.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three tight sentences: what it returns first, then the availability caveat, then the disclaimer. No filler, and each sentence carries distinct information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With an output schema present, return values need not be explained. The description covers the remaining agent-critical unknowns: provenance, that empty results are normal, and that the output is indicative rather than an official warning.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% and both parameters are documented there, including the default 72 and the 240 cap. The description only echoes the horizon concept ('future points within the horizon') and adds no syntax or format detail, so the baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a precise verb and resource ('Newest published water-level forecast for a station') and pins down the exact quantity returned (median of the state agency model run, future points within the horizon). This lets an agent distinguish it from get_readings (current observations) and get_flood_situation 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.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It gives a clear applicability condition ('Only gauges whose state publishes numeric forecasts have one, so an empty result is normal') and a framing caveat ('Indicative, not an official warning'). It does not explicitly name a sibling alternative for the case where no forecast exists, but the when-it-applies guidance is strong.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Time series for a station (downsampled to ≤200 points; history depth on this tier: last 90 days, default last 7 days). type "level" (default) → level series as stored valueCentimeters: centimetres above gauge zero for most gauges, but an elevation ×100 for groundwater wells and for gauges reporting an absolute elevation (Swiss gauges, the Neusiedler See) — divide by valueDivisor to read it in unit. type "discharge" → discharge Q in m³/s where the station provides it.
| Name | Required | Description | Default |
|---|---|---|---|
| to | No | ISO 8601 end, defaults to now | |
| from | No | ISO 8601 start, e.g. 2026-06-01T00:00:00Z | |
| type | No | Series type: level (default) or discharge (m³/s) | |
| stationId | Yes | Namespaced station id, e.g. "pegelonline:<uuid>" or "lhp:BY_10026301" |
| Name | Required | Description |
|---|---|---|
| note | No | Present when the series was downsampled |
| unit | No | Unit of a level series; absent for discharge |
| count | Yes | |
| summary | Yes | Min and max (level: in unit) and latest point; null when empty |
| readings | No | Level series as stored valueCentimeters |
| discharge | No | Discharge series, m³/s |
| stationId | Yes | |
| valueDivisor | No | Divide valueCentimeters by this to read in unit |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only/idempotent safety. Beyond that, the description discloses non-obvious behavior: series are downsampled to ≤200 points and history is capped at 90 days with a 7-day default. These operational constraints would not be discoverable from the structured fields.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The core constraints are front-loaded, but the Swiss-gauge / Neusiedler See aside and the valueCentimeters digression make the sentence dense and harder to scan. Information earns its place, but the packaging is heavy for a single paragraph.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 4-parameter read tool with full schema coverage and an output schema, the description is nearly complete: it covers depth, downsampling, units, and default type. Only the choice against sibling retrieval tools is left implicit.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
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 goes further by explaining what 'level' and 'discharge' actually mean, including unit semantics (centimetres above gauge zero, elevation ×100, divide by valueDivisor, m³/s), which the schema only labels.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Opens with a specific resource and scope: 'Time series for a station', which clearly distinguishes it from siblings like get_station, get_forecast and get_flood_situation. It does not explicitly name an alternative though, so it falls short of a 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description supplies useful contextual constraints (history depth 90 days on this tier, default 7 days, downsampling to ≤200 points) but never states when to choose this over get_forecast or search_stations. Usage is implied by the resource rather than directed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Master data of one station: measurement type, current value with its unit, thresholds (MNW/MHW, alert marks, as stored valueCentimeters), flood class, coordinates.
| Name | Required | Description | Default |
|---|---|---|---|
| stationId | Yes | Namespaced station id, e.g. "pegelonline:<uuid>" or "lhp:BY_10026301" |
| Name | Required | Description |
|---|---|---|
| id | Yes | |
| name | Yes | |
| unit | Yes | |
| water | Yes | |
| latitude | Yes | |
| longitude | Yes | |
| thresholds | Yes | |
| latestValue | Yes | Latest level, in `unit` |
| valueDivisor | Yes | Divide any valueCentimeters by this to read it in `unit` |
| measurementType | Yes | river | groundwater | sea_level | reservoir |
| latestMeasuredAt | Yes | |
| latestValueCentimeters | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds value by disclosing the payload contents, notably that thresholds are given as stored valueCentimeters with MNW/MHW and alert marks, but says nothing about freshness of the 'current value' or rate limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single dense sentence with the resource named up front followed by the field inventory. Nothing is wasted, though the parenthetical threshold detail makes it slightly list-like rather than fully front-loaded around the primary purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
An output schema exists, so return-value documentation is not strictly required, yet the description still summarizes the important fields and the unit convention for thresholds. Together with a fully documented single required parameter, an agent has enough to call it correctly; only station-id acquisition is left implicit.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, and the stationId parameter already documents both supported namespace formats (pegelonline:<uuid>, lhp:BY_10026301). The description adds no parameter-level detail, so the schema does the heavy lifting and baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (implicitly retrieves) and resource (master data of one station), then enumerates the returned fields: measurement type, current value with unit, thresholds, flood class, coordinates. This clearly separates it from sibling tools like search_stations (plural discovery) and get_readings (time series), though no sibling is named explicitly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is only implied: 'one station' suggests a single-station lookup requiring a station id, contrasting with search_stations. There is no explicit statement of when to use this versus get_readings or get_flood_situation, nor any prerequisite guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Daily weather forecast at the station coordinate (DWD data via Bright Sky).
| Name | Required | Description | Default |
|---|---|---|---|
| stationId | Yes | Namespaced station id, e.g. "pegelonline:<uuid>" or "lhp:BY_10026301" |
| Name | Required | Description |
|---|---|---|
| daily | Yes | |
| available | Yes | False when the forecast provider is unreachable |
| stationId | Yes | |
| attribution | Yes | |
| stationName | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful context about daily granularity and the underlying data source (DWD via Bright Sky), but it does not disclose rate limits, caching, freshness, or other operational behavior beyond the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single front-loaded sentence with no filler. Every element—daily granularity, station coordinate scope, and data source—earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple one-parameter read tool with full schema coverage, rich annotations, and an output schema, the description is largely complete: it identifies the resource, location basis, and data origin. The only notable gap is the lack of explicit sibling routing, which could matter when get_forecast is also present.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, and the single stationId parameter already includes format examples in the schema. The description implies that the station id resolves to a coordinate used for the forecast, which adds a little meaning, but it provides no additional syntax, constraints, or edge-case handling beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific resource (daily weather forecast), scope (at the station coordinate), and data source (DWD data via Bright Sky). It is clear enough to distinguish from water-level siblings like get_readings or get_flood_situation, but it does not explicitly differentiate from get_forecast, so it falls short of a 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description says what the tool returns but gives no when-to-use guidance, prerequisites, or alternatives among the six sibling tools. There is no indication of when to prefer get_weather over get_forecast or other forecast/observation tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search stations in Germany and its neighbouring countries — river gauges, groundwater wells, reservoirs, coastal gauges — by name or water body, optionally filtered by region (a German federal state or a country code). latestValue is given in the station's unit.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | Station or water name, e.g. "Köln" or "Rhein" | |
| federalState | No | ISO 3166-2 code for a German state, e.g. DE-NW; CH, AT, CZ, LU or FR for a country |
| Name | Required | Description |
|---|---|---|
| note | No | Present when the result was capped |
| stations | Yes | |
| totalMatches | Yes | Matches before the result cap |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the safe read-only, idempotent, open-world profile, so the description only needs to add context. It does add the geographic coverage and, usefully, the semantic that latestValue is expressed in the station's own unit, which is not derivable from the annotations or schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence with the core purpose front-loaded and the scenario list and filters following it; the em-dash enumeration of station types is slightly heavy but each item disambiguates scope. No filler or repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
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 with the unit note and filter semantics included the definition is sufficient to call the tool correctly. The only omission is routing to siblings (get_station by ID, get_readings for measurements), which would help in this crowded tool set.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% and both parameters are fully documented there, including the ISO 3166-2 example. The description's phrases 'by name or water body' and 'region (a German federal state or a country code)' restate the schema rather than adding new meaning, so the baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb ('Search') and resource ('stations') and enriches the resource with its subtypes (river gauges, groundwater wells, reservoirs, coastal gauges) and geographic scope. The verb/name contrast with the single-station sibling get_station is implicit rather than stated, so sibling differentiation is not explicit.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It tells the agent that the region filter is optional and what the two lookup modes are (by name or water body), which implies when to use each. But no alternative tool is named and there are no conditions for choosing search_stations over get_station or get_readings, so guidance stays implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
search_stations1 field changedInput schema / properties / federalState / descriptionPrevious value: -"ISO 3166-2 code for a German state, e.g. DE-NW; CH, AT or CZ for a country"New value: +"ISO 3166-2 code for a German state, e.g. DE-NW; CH, AT, CZ, LU or FR for a country"search_stations2 fields changedInput schema / properties / federalState / descriptionPrevious value: -"ISO 3166-2 code for a German state, e.g. DE-NW; CH or AT for a country"New value: +"ISO 3166-2 code for a German state, e.g. DE-NW; CH, AT or CZ for a country"Output schema / properties / stations / items / properties / unit / descriptionPrevious value: -"cm for rivers; m ü. NN / m ü. M. for wells and Swiss gauges"New value: +"cm over gauge zero; m ü. NN for wells; the datum unit (m ü. M., m ü. A.) for gauges reporting an absolute elevation"get_flood_situationget_forecastget_readingsget_stationget_weathersearch_stationsReal-time water levels and flow rates from USGS stream gauges
Access UK flood warnings, river levels, water quality, Met Office forecasts, and carbon data
River levels & flood alerts: USGS gauges. $0.01/query. Register in-session — free testnet funds.
Tankerkoenig MCP — German real-time fuel prices (Benzinpreise) for all