Skip to main content
Glama

One2Trip

Auto del viaggio

get_trip_car
Read-only

Stato dell'auto di una quotazione di quote_trip, che il server cerca dopo la risposta. Solo lettura: non lancia ricerche e non consuma quotazioni. Chiamalo con il quote_id quando car_status è searching, dopo aver mostrato volo e hotel, rispettando retry_after, al massimo 4 volte in tutto. Di solito l'auto è pronta entro 20 secondi; dopo 30 secondi senza risultato la ricerca è considerata fallita (error). car_status: found = auto trovata, total e per_person comprendono l'auto; unavailable = nessuna auto per quelle date; error = ricerca fallita; flight_changed = il volo scelto in chat ha orari diversi e l'auto si sceglie dal booking_url. Senza auto il totale resta quello di quote_trip; booking_url non cambia. Segui il testo che accompagna il risultato (posti e bagagliaio, condizioni per uscire dal paese).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "quote_id": "<quote_id>"
    },
    "name": "get_trip_car"
  }
}

Input Schema

NameRequiredDescriptionDefault
quote_idYesquote_id restituito da quote_trip.

Output Schema

NameRequiredDescriptionDefault
carYesAuto scelta, solo con found; altrimenti null.
totalNoTotale in euro per tutti i viaggiatori: con l'auto solo se found, altrimenti quello di quote_trip.
car_statusYesValori: searching = ricerca in corso; found = auto trovata; unavailable = nessuna auto per queste date; error = ricerca fallita; flight_changed = dopo una scelta in chat il volo ha orari diversi, l'auto si ricalcola sul sito.
per_personYesTotale a persona in euro, al centesimo, come sul sito (1224.5 = € 1.224,50).
retry_afterNoSolo con searching: secondi da attendere prima di richiamare get_trip_car. Di solito l'auto è pronta entro 20 secondi; dopo 30 secondi senza risultato la ricerca è considerata fallita (error).
cross_borderNoSolo con found e tappe in più paesi: condizioni del noleggiatore per uscire dal paese; il testo che accompagna il risultato dice come riferirle.
per_person_textNoIl totale a persona già scritto come sul sito (per esempio «€ 1.224,50»): da dire così com'è.
preference_noteNoSolo con found e preferences.car: nessuna auto trovata rispetta tutte le preferenze, questa è la più economica. Da riferire al cliente.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnlyHint and no destructiveness, yet the description adds substantial behavior: no new searches are launched, quotes are not consumed, typical readiness within ~20s, failure declared after 30s, and retry backoff via retry_after. It also discloses side effects on the result set (total unchanged without a car, booking_url unchanged) and the four car_status outcomes.

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

Conciseness4/5

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

Purpose and read-only guarantee are front-loaded, then the trigger condition, retry policy, timing budget and status semantics follow in a logical order. It is dense and long, and the car_status enumeration partially overlaps the output schema, but essentially every clause carries operational information.

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

Completeness5/5

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

An output schema exists, yet the description still explains the meaning of each status (found, unavailable, error, flight_changed) and the fallback via booking_url, plus tells the agent to follow accompanying text about seats, luggage and cross-border conditions. Nothing needed to call or interpret it is missing.

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

Parameters3/5

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

Only one parameter, fully documented in the schema (pattern and provenance from quote_trip), so the schema does the heavy lifting. The description reinforces the quote_id provenance and ties the call to a car_status precondition, but adds no format or validation detail beyond the schema.

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?

States a specific verb and resource — retrieving the car status of a quote_trip quotation — and names the sibling tool that produces the quote_id. An agent can distinguish it from quote_trip, stato_viaggio or attendi_viaggio 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?

Explicit preconditions and sequencing: call with quote_id when car_status is 'searching', only after showing flight and hotel, respecting retry_after, at most 4 times total. It also states what the tool does not do (non lancia ricerche, non consuma quotazioni), so misuse is hard.

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