Skip to main content
Glama

search_tourism

Read-only

Kuratierte Tourismus-Suche des Niedersachsen-Hubs: redaktionell gepflegte Einträge mit Veranstaltungen samt Datum, Preisen, Beschreibungen, Medien, Öffnungszeiten und Touren. Für „welche Veranstaltungen sind in X", „was kostet der Eintritt" ist dieses Werkzeug die Auskunft — erst verorten, dann abfragen: region/query aus der Frage, lat/lon nur aus search_place. Tool-Semantik-Abgrenzung: die in OpenStreetMap erfassten Sehenswürdigkeiten eines Gebiets listet expand_kg_pois; für Region-Tourismus dürfen beide laufen. Umkreis um einen Punkt → nearby, welcher Ort gemeint ist → search_place. When to use: Events — DE: „was ist diese Woche/am Wochenende in los", „Veranstaltungen in ". EN: „events in this weekend". Unterkünfte/Gastro — DE: „Hotels in ", „Restaurants in ". EN: „hotels/restaurants in ". Touren — DE: „touristische Radrouten/Radtouren in ", „Radwanderwege/Wanderwege am " → type=tour; jede Tour trägt dann length_m, duration_min, ascent_m/descent_m, round_trip und activities (wörtlich, als was der Datensatz sie führt: „Fahrrad", „E-Bike", „Wandern", „Kanu") sowie trail_shape (round | line | ascent, aus dem Verlauf gelesen — gilt vor round_trip) — DARAN auswählen, nicht am Namen. Die ersten 5 Touren mit Verlauf tragen ihn als path_polyline für die Karte (Encoded Polyline, ≤ 40 Punkte) — nicht vorlesen. Bei mehreren die passendste per get_tourism_details zeichnen, die anderen nennen und fragen, welche noch. When NOT to use: alle in OpenStreetMap erfassten Sehenswürdigkeiten → expand_kg_pois; Detail zu EINEM Treffer → get_tourism_details; Routing/ Abfahrten, auch „von A nach B mit dem Rad" → der Server MobilityMCP; Wetter/Tide → get_current_weather/get_tide. Required args: region ODER query (eines von beiden — Freitext-Region/ Name, z.B. region="Wangerland", query="Sielhafenmuseum"). Optional: type (genau eines von "event" | "poi" | "accommodation" (="hotel") | "gastro" (="restaurant") | "tour" — kuratierte Rad-/Wander-Routen, auch als "radtour"/"radroute"/"radwanderweg"/"wanderweg" akzeptiert; weggelassen = alle Typen; unbekannter Wert = alle. OHNE type=tour sind Touren praktisch nie unter den Treffern). Im Aktivitäts-Scope (type="poi"/"attraction"/"unternehmen"/…) sind Unterkünfte AUSGESCHLOSSEN, im Region- wie im Vicinity-Modus (ein Hotel ist keine Unternehmung); für Hotels explizit type="accommodation". timeframe (nur für type=event: "today" | "tomorrow" | "weekend" | "this_week" | "month" | ISO "YYYY-MM-DD" | Range "YYYY-MM-DD..YYYY-MM-DD"; ohne timeframe = kommende Events ab heute), limit, family_only (bool, Default false — nur die kuratierten Family-Kategorien, je mit der belegten suitability-Achse), indoor_only (bool — nur, was der Niedersachsen-Hub als „Schlechtwetterangebot“ führt; „drinnen“ führt er nicht. Andere Quellen entfallen, note sagt es). activity (nur mit type=tour): wie eine Tour zurückgelegt wird — "wandern" | "fahrrad" | "kanu" + Synonyme. Filtert auf die GANZE Familie kuratierter Aktivitätswerte; weglassen oder unbekannt = alle. shade (nur mit type=tour): "schattig" (überwiegend unter Bäumen) | "vormittags" | "mittags" | "nachmittags" (9–11/12–14/14–17 Uhr überwiegend im Schatten) am date (YYYY-MM-DD, Vorgabe heute) — nur solche Touren, danach sortiert, Stichtag in shade_day. Laubzeit Mai bis einschließlich Oktober, sonst shade_trees_leafless: nur Hang- und Gebäudeschatten. shade_tree_share = Anteil der Strecke unter Bäumen, nicht Schatten je Stunde. Aus LGLN-Höhenmodell und Luftbild; davon nur Anteile und Uhrzeiten wiedergeben, ohne Zusatz; shade_sources[].licence wie license wiedergeben. Was nicht beurteilt ist, sagt note. Coord-Vicinity-Modus (Umkreis, POI-Anker): für „ am/bei " den POI ZUERST über die Ortsauflösung zu einer Coord auflösen, dann lat+lon setzen (beide nötig, optional radius_m). region/query sind dann nur Pool-Hint; Treffer im Umkreis, nächster zuerst, je mit distance_m. NUR in diesem Modus kommt die OSM-Breite dazu, entdoppelt gegen die Kuration (kuratierter Treffer gewinnt): bei type=gastro die amenity-Gastronomie, im Aktivitäts-Scope (type=poi, „unternehmen") tourism ∈ attraction/museum/…, historic und leisure ∈ park/garden/… — AUSGESCHLOSSEN bleiben Unterkünfte (hotel/hostel) und Alltags-Versorgung (shop, Apotheke/Bank/Arzt), beides keine Ausflugsziele. Typical chain: search_tourism(region=<R>, type=event) → get_tourism_details(id) pro Treffer. Multi-call: ein Call pro Region/Typ. Anti-Fab note: Event-Namen, DATEN, PREISE, POI-Namen, Adressen kommen AUSSCHLIESSLICH aus pois[] / events[] dieses Aufrufs. returned: 0 / pois: [] / events: [] heißt: für war nichts abrufbar — so wiedergeben. Datum eines Events ist tool-belegt (events[].date / pois[].date, ISO-8601 Europe/Berlin) ODER abwesend — NIE geschätzt. DZT-Bündelung (zweite kuratierte Quelle, DE-weit): kuratierte Treffer AUSSERHALB Niedersachsens kommen aus der DZT-KG (Deutsche Zentrale für Tourismus), de-dupliziert; in Niedersachsen gewinnt der Niedersachsen-Hub-Eintrag. Bei type=tour bleibt sie AUSSEN VOR — sie führt keinen Touren-Inhaltstyp; kuratierte Touren gibt es nur für Niedersachsen, außerhalb ehrlich "keine Tour abrufbar". Returns {place, source:'niedersachsen-hub', type, returned, mode?, center?, radius_m?, shade_day?, shade_day_text?, shade_trees_leafless?, shade_sources?, pois:[{name,type,description?,address?,uri?,date?,price?,media?, coord?,opening_hours?,id?,distance_m?,source?,license?,hub_detail_url?, length_m?,duration_min?,ascent_m?,descent_m?,round_trip?,trail_shape?,activities?, shade_tree_share?,path_polyline?}], events:[{name,date,location,source?,license?}]}. Die Herkunft eines Treffers sagt sein source ('osm' | 'niedersachsen-hub' | 'dzt'). id ist der Schlüssel für get_tourism_details; die Felder folgen schema.org. license (additiv, PRO Treffer): die Lizenz, die der Datensatz selbst angibt — {id?, url?, notice?, holder?}: id = Lizenz-Kennung (z.B. 'CC-BY-SA-4.0', 'CC0-1.0', 'ODbL-1.0'), url = Lizenz-Text/Deed, notice = der WÖRTLICH wiederzugebende Lizenzverweis (DZT-copyrightNotice, § 3 der DZT-Nutzerbedingungen; bei OSM-Treffern die ODbL-Namensnennung), holder = der zu nennende Urheber (das author- bzw. copyrightHolder-Feld des Datensatzes). Gibt er nichts an, ist das Feld abwesend — nie eine geratene Vorgabe-Lizenz. Nennst du einen Treffer mit license.holder, nenne den Urheber mit. hub_detail_url (additiv, PRO Treffer, nur bei source: 'niedersachsen-hub'): die Entitätsseite dieses Treffers beim Niedersachsen-Hub, dem Nutzer nennbar — NICHT die Betreiber-Website (uri). Jeder Treffer, dessen Art beim Hub eine Eintragsseite hat, trägt sie: POI (p_…), Tour (t_…), Veranstaltung (e_…), Unterkunft (h_…), Gastronomie (g_…), Gebiet (r_…). Ein Medien-Datensatz (m_…) hat keine und trägt keine; fehlt sie, keine konstruieren. Mit family_only trägt jeder Treffer zusätzlich family, suitability ({family, age_bands, pushchair, seal (Kinderferienland-Siegel), indoor_bad_weather}) und, wo die Quelle sie führt, price_child/price_family — alle feature-belegt: „kinderfreundlich" ist belegt, nicht geraten.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_tourism"
  }
}

Input Schema

NameRequiredDescriptionDefault
latNoCoord-vicinity mode — center latitude. When `lat` AND `lon` are both given the search becomes a vicinity search around the point: only curated hits within `radius_m` are returned (proximity-filtered on the `coord` field), sorted nearest-first with an additive `distance_m`. Use it for POI-anchor questions ("Restaurants am Maschsee"): resolve the POI to a coord first, then pass it here. `region`/`query` then act as the enclosing-city candidate-pool hint (and are no longer required).
lonNoCoord-vicinity center longitude (paired with `lat`).
dateNoThe day `shade` is judged for, "YYYY-MM-DD"; today in Germany when omitted. Answered from the nearest computed day (`shade_day`). May to October inclusive is the leaf season; outside it the trees are bare and only slopes and buildings shade.
typeNoContent type to narrow the search. One of: "event", "poi", "accommodation" (a.k.a. "hotel"), "gastro" (a.k.a. "restaurant"), "tour". Omit to search across all curated types. Unknown values are treated as "all" (never an error).
limitNoMaximum number of curated entities to return (default 8, clamped 1..=20).
queryNoFree-text query (name / keyword) when not searching a whole region, e.g. "Sielhafenmuseum". Alias for `region`; one of the two is required.
shadeNoOnly TOURS mostly in shade, for `type=tour`, ordered by it: "schattig" (mostly under trees) or "vormittags" / "mittags" / "nachmittags" (mostly in shade 9–11 / 12–14 / 14–17 o'clock) on the day `date`. Computed from LGLN height and aerial data; pass on its shares and hours, nothing more. An unrecognised word filters nothing; with another `type` it has no effect and `note` says so.
regionNoRegion or place to search within, as free text (e.g. "Wangerland", "Hooksiel", "Hannover"). Either `region` or `query` must be given; `region` is the natural choice for a place-scoped tourism search.
activityNoHow a TOUR is travelled, for `type=tour`: "wandern" (also "wanderweg", "spaziergang", "hiking", "zu Fuß"), "fahrrad" (also "radtour", "e-bike", "mountainbike", "cycling") or "kanu" (also "paddeln", "SUP"). Each word selects the whole family of curated activity values, so a hiking question also finds the records filed under "Winterwandern", "Nordic Walking" or "Spaziergang" — 8 % of the walked ones carry no "Wandern" value at all. Which value a given record carries is on the record (`activities`). Omit to search every activity; an unrecognised word is treated as "all" (never an error).
radius_mNoCoord-vicinity radius in metres (default 2000, clamped 100..=20000).
timeframeNoOptional event-date window for `type=event`: "today", "tomorrow", "weekend", "this_week", "month", or an explicit ISO date "YYYY-MM-DD" / range "YYYY-MM-DD..YYYY-MM-DD". With no timeframe the additive `events` list defaults to upcoming events (today onward).
family_onlyNoFamily mode: search the curated NDS family categories (Tierpark/Freizeitpark/Spielplatz/Erlebnisbad/Badesee/Kletterpark/…) and overlay the curated suitability axis (age bands, Kinderwagentauglich, Kinderferienland-Siegel, Schlechtwetterangebot). Every record is then family-belegt + carries an additive `suitability` object. Defaults false.
indoor_onlyNoKeep only what the Niedersachsen-Hub marks as „Schlechtwetterangebot" (also `suitability.indoor_bad_weather`) — the source carries no attribute „indoor", this is the nearest it has. On any search; sources without that mark are then not asked, and the answer says so in `note`.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / date
      Added value: +{
      +  "description": "The day `shade` is judged for, \"YYYY-MM-DD\"; today in Germany when\nomitted. Answered from the nearest computed day (`shade_day`).\nMay to October inclusive is the leaf season; outside it the trees are\nbare and only slopes and buildings shade.",
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • changedInput schema / properties / shade / description
      Previous value: -"Only TOURS mostly in shade, for `type=tour`, ordered by it: \"schattig\"\n(mostly under trees) or \"vormittags\" / \"mittags\" / \"nachmittags\" (mostly in\nshade 9–11 / 12–14 / 14–17 o'clock on 21 June). Computed from LGLN height\nand aerial data; infer no weather, temperature or UV from it. An\nunrecognised word filters nothing; with another `type` it has no effect\nand `note` says so."New value: +"Only TOURS mostly in shade, for `type=tour`, ordered by it: \"schattig\"\n(mostly under trees) or \"vormittags\" / \"mittags\" / \"nachmittags\" (mostly in\nshade 9–11 / 12–14 / 14–17 o'clock) on the day `date`. Computed from LGLN\nheight and aerial data; pass on its shares and hours, nothing more. An\nunrecognised word filters nothing; with another `type` it has no effect\nand `note` says so."
  2. Changed1 schema field changed
    • changedInput schema / properties / shade / description
      Previous value: -"Only TOURS mostly in shade, for `type=tour`, ordered by it: \"schattig\"\n(mostly under trees) or \"vormittags\" / \"mittags\" / \"nachmittags\" (mostly in\nshade 9–11 / 12–14 / 14–17 o'clock on 21 June). Computed from LGLN height\nmodels and aerial photos, nothing about weather, temperature or UV. An\nunrecognised word filters nothing; with another `type` it has no effect\nand `note` says so."New value: +"Only TOURS mostly in shade, for `type=tour`, ordered by it: \"schattig\"\n(mostly under trees) or \"vormittags\" / \"mittags\" / \"nachmittags\" (mostly in\nshade 9–11 / 12–14 / 14–17 o'clock on 21 June). Computed from LGLN height\nand aerial data; infer no weather, temperature or UV from it. An\nunrecognised word filters nothing; with another `type` it has no effect\nand `note` says so."
  3. Changed1 schema field changed
    • addedInput schema / properties / shade
      Added value: +{
      +  "description": "Only TOURS mostly in shade, for `type=tour`, ordered by it: \"schattig\"\n(mostly under trees) or \"vormittags\" / \"mittags\" / \"nachmittags\" (mostly in\nshade 9–11 / 12–14 / 14–17 o'clock on 21 June). Computed from LGLN height\nmodels and aerial photos, nothing about weather, temperature or UV. An\nunrecognised word filters nothing; with another `type` it has no effect\nand `note` says so.",
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
  4. Changed1 schema field changed
    • changedInput schema / properties / indoor_only / description
      Previous value: -"Restrict to rain-safe family records (the\n`suitability.indoor_bad_weather` / Schlechtwetterangebot proxy). Only\nmeaningful with `family_only=true`."New value: +"Keep only what the Niedersachsen-Hub marks as „Schlechtwetterangebot\" (also\n`suitability.indoor_bad_weather`) — the source carries no attribute\n„indoor\", this is the nearest it has. On any search; sources without that\nmark are then not asked, and the answer says so in `note`."
  5. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Read-only and open-world are already in annotations, but the description adds far more: source precedence (NDS hub > DZT > OSM), OSM inclusion only in vicinity mode, dedup rules, the anti-fabrication rule for names/dates/prices, per-hit `license` obligations, `hub_detail_url` key conventions, and the DZT tour exclusion. This is rich behavioral disclosure beyond structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

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

The description is front-loaded well, using bold section headers (semantics, when to use, required args, returns, licensing) that make it navigable. But it is extremely long for a 13-param tool, and several passages (licensing fields, hub_detail_url id prefixes, shade provenance) are verbose and partly duplicate the 100%-covered schema, so not every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description compensates by sketching the full return shape, source field, `id` as the details key, additive fields (`distance_m`, `suitability`, `license`, `hub_detail_url`), and empty-result semantics. It is nearly complete for a tool of this complexity, though it is so dense that some distinctions (e.g., `pois[]` vs `events[]` date fields) risk being lost.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema itself already documents each parameter thoroughly, so the description's restatement of most args adds limited marginal value. However, it does add cross-parameter semantics the schema does not spell out: tours are practically unreachable without `type=tour`, accommodation is excluded from the activity scope, `shade`/`activity` only apply with `type=tour`, and the `region`-vs-`query`/`lat`+`lon` mode switch.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

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

The opening sentence names a specific verb+resource (curated tourism search of the Niedersachsen hub) and enumerates the payload: events with dates, prices, descriptions, media, opening hours, tours. It explicitly separates itself from `expand_kg_pois`, `nearby`, `search_place`, `get_tourism_details`, and the mobility server, so an agent can pick it without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit when-to-use patterns in DE and EN per content type (events, hotels, restaurants, tours), a when-NOT-to-use block routing each case to the correct sibling, and a typical chain (`search_tourism` → `get_tourism_details`). Multi-call guidance (one call per region/type) is also stated.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources