List German cities that changed (raised or newly introduced) their Zweitwohnungsteuer in a given year — the fresh-news angle. Only 2026 is curated, and it is the default: 12 cities changed their rate, led by Potsdam (25 %), Borkum (22 %), Stuttgart (20 %). Every entry checked individually against the municipality's own statute.
| Name | Required | Description | Default |
|---|---|---|---|
| year | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the transparency burden and does a strong job: it discloses curation limits ('Only 2026 is curated'), data verification ('every entry checked individually against the municipality's own statute'), and expected output flavor (12 cities, led by Potsdam 25%, Borkum 22%, Stuttgart 20%). It does not describe what happens for non-curated years, but the curation caveat covers the main behavioral risk.
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: the first states the core purpose, the second adds the critical curation/default context with concrete examples, and the third reassures data quality. Every sentence earns its place and the most important information is front-loaded.
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?
Given one simple parameter, no output schema, and no annotations, the description is largely complete: it defines the domain, scope, data curation status, default year, and verification standard. It does not specify the exact return format, but 'List' strongly implies a list output, and the missing detail is minor for an agent deciding whether to call it.
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 0%, so the description must clarify the year parameter. It does: 'in a given year' explains the semantic role of the parameter, and 'Only 2026 is curated, and it is the default' adds crucial meaning beyond the schema's default value. It could be even more explicit about accepted year range, but the schema already supplies min/max.
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 action ('List German cities'), a concrete domain ('Zweitwohnungsteuer'), and a precise scope ('changed ... in a given year'), including what counts as a change ('raised or newly introduced'). The 'fresh-news angle' and focus on year-over-year changes distinguish it clearly from sibling tools like lookup, ranking, and by_state.
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 sets clear usage context: use this tool for a change-focused, news-oriented view of Zweitwohnungsteuer by year. It also gives a concrete usage warning that only 2026 is curated and defaults to it, but it does not explicitly name alternatives or state when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct tax/domain and operation: state-level aggregation, per-city lookup, ranking, and yearly change tracking are clearly separated per tax. The only potential overlap between state averages and city rankings is resolved by explicit descriptions of the state vs. city scope.
The two tax areas follow a perfectly parallel pattern: <tax>_by_state, <tax>_changes, <tax>_lookup, and <tax>_ranking. The utility tools list_datasets and pfaendung_calc also use clear snake_case names and do not disrupt the overall convention.
Ten tools is well-scoped for a server covering two municipal taxes and a garnishment calculator. Each tax has four natural query operations, plus dataset discovery and a separate calculation tool, with no redundant or missing categories.
For a read-only data server, the surface is complete: per-city lookup, ranking, state aggregation, and change tracking exist for both taxes, list_datasets exposes dataset metadata, and pfaendung_calc covers the garnishment computation. There are no obvious dead-end workflows within the stated domain.