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

Annotations already cover readOnlyHint and openWorldHint, so the bar is lower; the description adds substantial operational constraints: lat/lon must come from search_place and never be guessed, weather values must only come from this tool's output (anti-fabrication), and legal attribution to Deutscher Wetterdienst/GeoNutzV is required. This goes well beyond the structured 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 well-structured with bold labels and front-loaded purpose. It is longer than average, and the opening overlaps somewhat with the 'When to use' section, but nearly every sentence earns its place with operational or routing guidance.

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 tool without an output schema, it covers what data will be returned (temperature, conditions, wind, humidity), the attribution object, and the one-call-per-place behavior. An agent has enough context to invoke the tool correctly and interpret its results, though exact response field names are not specified.

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 baseline is 3. The description adds the crucial rule that lat/lon must originate from search_place rather than estimation, and clarifies unit options with temperature symbols. It mostly restates schema defaults for lang and units, but the sourcing constraint is meaningful extra semantics.

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 opening line states the tool returns current weather for coordinates and explicitly positions it as the answer source for 'wie ist das Wetter in X', distinguishing it from general knowledge. It also contrasts itself with get_weather_forecast and get_tide, so the agent can clearly differentiate it among siblings.

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 has explicit 'When to use' and 'When NOT to use' sections naming alternatives: get_weather_forecast for forecasts beyond one hour and get_tide for tides. It also provides a typical chain (search_place → this tool) and multi-call guidance, leaving no ambiguity about when to select it.

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