experiences-oracle

Cerca esperienze, tour e biglietti

search_experiences

Read-only

Cerca tour, attività ed esperienze da prenotare in un luogo o per un intento di viaggio (es. "cosa fare a Roma", "biglietti per il Colosseo", "tour in barca a Capri"). Restituisce risultati reali con città, prezzo, rating e un link di prenotazione (redirect PIQOD affiliato). USA QUESTO TOOL quando l'utente cerca cose da fare, tour, attività, biglietti o esperienze in una destinazione. IMPORTANTE per la coerenza: se l'utente nomina un'ATTRAZIONE/attività precisa (es. "tour del Colosseo"), passa quel nome in keyword (es. "Colosseo") → i risultati saranno SUL Colosseo, non genericamente vicini. Mappa anche gli INTENTI sui filtri: "salta fila/skip the line" → skip_the_line=True; "più economico/cheapest" → sort="price"; "cancellazione gratuita" → free_cancellation=True; "con bambini/per famiglie" → traveler_type="famiglie", "romantico/in coppia" → "coppie"; "la sera/di notte/al tramonto" → day_part="sera", "la mattina/all'alba" → "mattina", "il pomeriggio" → "pomeriggio".

Nel risultato (lo stesso testo delle azioni GPT, api/oracle_openapi):
    min_people: Minimo di persone per prenotare, solo se il provider lo chiede ed è 2 o più: dillo accanto al
        prezzo («minimo 2 persone»). null = nessuno o ignoto. price_from non è il totale: a persona se
        price_basis=PER_PERSON, per unità se UNIT; con price_basis '' scrivi «minimo N persone» senza «a persona».
    price_basis: PER_PERSON | UNIT (prezzo per veicolo/gruppo/barca) | '' = dato non fornito dal provider (oggi
        disponibile sui prodotti Viator arricchiti; copertura in crescita).
    price_unit: VEHICLE/GROUP/BOAT/... quando price_basis=UNIT; altrimenti ''.

Args:
    query: intento o luogo dell'utente.
    location: luogo esplicito (override di query), opzionale.
    category: categoria/filtro tematico, opzionale.
    budget_max: prezzo massimo, opzionale.
    keyword: attrazione/attività specifica da matchare nei titoli (es. "Colosseo").
    skip_the_line: True se l'utente vuole biglietti/tour "salta fila".
    free_cancellation: True se vuole cancellazione gratuita.
    sort: "price" per i più economici prima (default "rating").
    limit: numero risultati (max 50).
    traveler_type: "famiglie" | "coppie", opzionale.
    day_part: "mattina" | "pomeriggio" | "sera" (quando inizia l'esperienza), opzionale.

Input Schema

TableJSON Schema

Name	Required	Default
`sort`	No	rating
`limit`	No
`query`	Yes
`keyword`	No
`category`	No
`day_part`	No
`location`	No
`budget_max`	No
`skip_the_line`	No
`traveler_type`	No
`free_cancellation`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 28, 2026

addedInput schema / properties / day_part

Added value: +{
+  "default": "",
+  "title": "Day Part",
+  "type": "string"
+}

addedInput schema / properties / traveler_type

Added value: +{
+  "default": "",
+  "title": "Traveler Type",
+  "type": "string"
+}

Changed1 schema field changedJun 27, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "title": "search_experiencesDictOutput",
+  "type": "object"
+}

First observedJun 27, 2026

TDQS

A4.1/5.0

Behavior4/5

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

The annotations already establish readOnly, openWorld and non-destructive behavior. The description adds useful context beyond that: results are real, include city, price, rating and an affiliate booking redirect (PIQOD). It does not mention rate limits or pagination, but it goes meaningfully beyond the annotation profile.

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 with purpose and usage, but it contains a long block explaining output fields such as min_people, price_basis and price_unit. Since an output schema exists, much of that return-value detail is likely redundant and makes the definition longer than necessary.

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?

For an 11-parameter search tool, the definition is nearly complete: it covers purpose, usage triggers, parameter meanings and intent mapping. The main gap is sibling differentiation, and the return-value explanation is arguably unnecessary given the output schema.

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

Parameters5/5

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

With 0% schema description coverage, the description fully compensates by explaining every one of the 11 arguments, including enum-like values for traveler_type, day_part and sort, the default and max for limit, and how keyword differs from query. The intent-to-filter mapping further clarifies how to populate filters from natural language.

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

Purpose4/5

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

The description states a clear verb and resource: search for tours, activities and experiences to book by location or travel intent, with examples. However, it never distinguishes this tool from its siblings compare_experience or get_destination_guide, so an agent must infer the boundary itself.

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

Usage Guidelines4/5

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

It explicitly says to use this tool when the user looks for things to do, tours, activities, tickets or experiences in a destination. It gives concrete intent-to-filter mapping, which is strong usage guidance, but it does not state when not to use it or name the alternative siblings.

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

All experiences-oracle tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?