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

Annotations already declare readOnlyHint, openWorldHint, and destructiveHint, and the description adds valuable context beyond them: forecast values must come only from the tool output (anti-fabrication), coordinates must originate from search_place, one call per place, multi-day queries via limit, and the mandatory GeoNutzV attribution naming Deutscher Wetterdienst. This significantly enriches the behavioral contract without contradicting any annotation.

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 long but densely structured with bolded labels ('When to use', 'When NOT to use', 'Required args', 'Typical chain', 'Multi-call', 'Anti-Fab note', 'attribution'). Purpose is front-loaded, and every section earns its place by conveying a distinct operational rule. No filler or tautology.

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?

Despite having no output schema, the description covers all needed call context: parameter semantics, chaining, multi-call behavior, data integrity rules, and attribution obligations. The absence of a return-structure description is mitigated by the instruction that forecast values come exclusively from tool output, and the agent can inspect the actual response at runtime.

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 adds meaning beyond the schema: it marks lat/lon as required and sourced from search_place (never self-estimated), explains limit as forecast slots that span multi-day queries, and lists units and lang with their defaults and examples. This is substantive semantic guidance, not mere repetition.

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 opens with a specific verb+resource: 'Wetter-Vorhersage zu Koordinaten' (weather forecast to coordinates) and explicitly states this tool is the answer for 'wie wird das Wetter morgen in X'. It also differentiates from siblings by naming get_current_weather and get_tide as the tools for current conditions and tides, so an agent can disambiguate immediately.

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 provides explicit 'When to use' and 'When NOT to use' sections with concrete examples in both German and English, and names the exact sibling tools to use instead. It also gives a typical chain (search_place → THIS_TOOL → optional POI tools) and a multi-call rule, leaving no ambiguity about when to select this tool.

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