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

Annotations already cover readOnly/openWorld/non-destructive, but the description adds real behavior: a fallback to hourly forecast values when the nowcast is stale, a statement that the response flags this, a disclaimer that it is not an official severe-weather warning, and an instruction to cite the data source with license.

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-loads the core scope, then fallback behavior, disclaimer, examples and output instruction. The example questions and the citation instruction are useful but add length; still every part serves a 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?

With no output schema, the description carries the return-value burden and does so adequately by explaining the 15-minute nowcast, the hourly fallback, and that source/license appear at the end of the summary. Nothing critical for correct invocation is missing, though return-format details remain thin.

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 'ort' parameter is already fully documented with accepted formats (municipality, GKZ, coordinates). The description adds no syntax 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.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource with scope: precipitation for the next 3 hours in 15-minute steps for an Austrian municipality, plus temperature, wind and gusts. It also implicitly distinguishes itself from wetter_prognose by scoping to the near-term nowcast window.

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?

Example questions ('Regnet es gleich in Linz?', 'Wann hört der Regen in Graz auf?') make the intended use concrete, and the fallback to hourly forecast values is described. It doesn't explicitly name sibling tools like wetter_prognose as alternatives, so a 4 rather than 5.

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