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

Annotations already declare readOnly/openWorld/non-destructive, so the safety profile is covered. The description adds real behavioral context beyond them: a hard cap of 20 results sorted by distance, hourly data refresh, a 'not an official warning' disclaimer, and the requirement to cite the data source with license in the answer. It does not state what happens when the radius returns more than 20 stations, but overall this 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.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core purpose, then scope, then attributes, then examples, then the citation instruction – a sensible ordering. It is somewhat long, and the closing 'Nenne in deiner Antwort die Datenquelle…' instruction is output guidance rather than tool selection help, but every sentence still carries 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 no output schema, the description carries the full burden and does so: it enumerates the per-station fields (Gewässer, Wert mit Einheit, Messzeitpunkt, Lage/Stufe, Tendenz), the result ordering and cap, the data freshness, and the disclaimer. An agent has everything needed to call it and interpret the response.

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%, so both parameters (ort with its Gemeinde/GKZ/Koordinate forms, radius_km 1–100 default 15) are already fully documented. The description only restates the geographic scope (Austrian municipality) and adds nothing about accepted input forms or units, so 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 resource (Pegelmessstellen des Hydrographischen Dienstes), the scope constraint (Umkreis einer österreichischen Gemeinde, nach Entfernung sortiert, höchstens 20), and the returned attributes. It is clearly distinguishable from siblings like pegel_an_gewaesser (gauges on one water body) and hochwasserlage (flood situation overview), since it is explicitly a proximity search around a place.

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?

Three concrete example questions ("Wie hoch ist die Enns in Steyr?", "Welche Pegel gibt es rund um Schärding?") make the intended use case unambiguous, and "Keine amtliche Warnung" implicitly marks the boundary with the flood-warning sibling hochwasserlage. What is missing is an explicit routing statement naming the alternative tool for official warnings.

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