Skip to main content
Glama

Google Flights Search (Real-Time Fares)

FlightPowers: search round-trip flights

search_roundtrip_flights
Read-only

FlightPowers round-trip fare search: live prices read from Google Flights, priced as paired legs rather than two separate one-ways. Input: origin and destination IATA codes -- the destination may be several codes, as "BCN,LIS,ATH" or ["BCN","LIS","ATH"] -- a departure date or range, and either a return date or a trip length in nights. Returns the total price for both legs, per-leg airline, stops and duration, and a single bookable buy_link for the trip.

Use it for any return-trip fare question. For a flexible search make ONE call: pass departure_date_from / departure_date_to for the outbound range and nights instead of return_date to compare trip lengths -- '5 to 7 nights in Rome sometime in May' is one call.

A WHOLE MONTH is one call too. departure_date_from "2026-10-01", departure_date_to "2026-10-31" and nights [3, 4, 5] prices every departure day in October at three trip lengths and tells you which combination is cheapest. That is 93 date/night combinations and the cap rises to cover them by itself -- do not narrow the question to make it fit, and do not split it into several calls.

Each date/night/destination combination is ONE request billed to the caller's plan, so a month at three trip lengths costs 93 of them and the same month across two destinations costs 186. Say that number before running a search that large if the user has not asked for it in so many words. A search that fails with a server error is retried once and RapidAPI bills the retry, so the figure to quote back is api_usage.hub_requests_billed (what the plan was actually charged), not the combination count. Both come back in api_usage, with the plan's remaining quota.

by_destination carries one entry per destination you asked for -- empty ones included, each with a reason -- so read it before telling a user a destination has no flights.

Requires the caller's own RapidAPI key for the Google Flights Live API. Get one (free tier available) at https://rapidapi.com/mtnrabi/api/google-flights-live-api, then pass it as an x-rapidapi-key header (preferred), a ?rapidapi_key= query parameter on the server URL, or your client's own API key field -- first non-empty wins. Usage counts against the caller's own RapidAPI plan, not ours; every response reports what it spent and what is left in api_usage. No key? Sign in with Google and the first 10 searches each day are free on this server -- ad-free, nothing to paste. Connect your own RapidAPI key at https://flights.flightpowers.com/connect to remove the cap.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum trips to return, after merging and sorting.
nightsNoTrip length in nights; a number, or a list like [5, 6, 7]. The return date is derived from each departure date.
sort_byNo"best", "price", or "duration". Applied across all results.best
verboseNoReturn every field the upstream sends on each fare, and every fare that was selected, with no row bound. Off by default: a result carries the best rows by your sort_by in a compact shape (dates, destination, airline, stops, duration, price, trip length and the booking link), because a wide search over a month and several destinations otherwise produces a megabyte of JSON that some hosts refuse to put in the conversation at all. Turn it on when you need the arrival times, the per-leg stop counts, the raw stop details or more rows than results_returned; results_total always says how many there were.
currencyNoISO currency code, default "usd".usd
max_priceNoOnly return trips at or below this total price.
seat_typeNo1 economy, 2 premium economy, 3 business, 4 first.
passengersNoOne entry per traveller, not a count: 1 adult, 2 child (aged 2-11), 3 infant on lap, 4 infant in seat, e.g. [1, 1, 2] for two adults and a child. At least one adult, each infant on lap needs its own adult, at most 9. Omit for one adult. A counts list [adults, children, infants], e.g. [2, 1, 0], or a bare [2] for two adults, is recognised and converted to codes before the search; a list that is valid as codes is searched as codes.
to_airportYesDestination airport. One IATA code ("BCN"), several separated by commas ("BCN,LIS,ATH"), or a list (["BCN","LIS","ATH"]) -- every shape is accepted and the destinations are compared in the same search.
return_dateNoFixed return date. Use this OR nights, not both.
from_airportYesOrigin IATA code, e.g. "TLV". One origin per search; a second one is refused rather than searched.
max_searchesNoThe billed requests this call may make, up or down. Leave it out for the normal behaviour: the cap covers the request when the request is reasonable (a whole month at three trip lengths is 93 combinations and a whole month x 3 nights x 3 destinations is 279; both run in full) and anything past it is sampled evenly across the range rather than cut short. Set it lower to spend less of the plan's quota on a wide search, or higher -- to a hard maximum of 300 -- for a grid wider than that.
use_fallbackNoLeave unset. Switches the search to a second, independent flight data source instead of the usual Google Flights page read. Unset already escalates to that source once, automatically, after a search's retries have failed. true forces it inline on every attempt -- much slower, and it can time out. false disables it entirely, that automatic retry included.
departure_dateNoSingle outbound date, "YYYY-MM-DD".
max_return_stopsNoMaximum stops on the return leg.
departure_date_toNoLast date of an outbound range.
departure_date_fromNoFirst date of an outbound range.
max_departure_stopsNoMaximum stops on the outbound leg.
return_airline_codesNoRestrict the return leg to these airlines.
departure_airline_codesNoRestrict the outbound leg to these airlines.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
messageNoPresent when there is something the model must relay to the user rather than silently absorb -- no results, a degraded search, a missing key or a spent quota.
partialNoPresent when some searches failed but others succeeded. Plain text saying how much of the request the results cover.
resultsYesThe fares found, already sorted and deduplicated. An empty array is only meaningful when search_status is 'empty'. This is the TOP results_returned of results_total rows by the sort you asked for -- cheapest first by default, shortest first on sort_by 'duration' -- with every destination that has fares still represented. Each row is in a compact shape: destination, the date or dates, trip length in nights on a round trip, airline (both legs on a round trip), stops, duration, the price as a string and a number, Google's price band with its verdict, and the booking link. The origin is on the response as from_airport rather than repeated on every row. Arrival descriptions, per-leg stop counts, raw stop details and the duration in seconds are dropped; `verbose: true` returns them, and every row that was selected, on that call.
api_usageNoWhat this call cost the caller's own RapidAPI plan, and what remains on it. Present on every response that reached the upstream, including a degraded one -- a search that failed was still billed.
signup_urlNoWhere the caller subscribes or changes plan.
from_airportNoThe origin, as the upstream renders it ('Tel Aviv (TLV)'). One origin per search, so it is on the response rather than repeated on every row.
result_countNoHow many rows are in `results`; same as results_returned.
needs_api_keyNoTrue when no usable RapidAPI key arrived with the call, or the upstream rejected the one that did. No search was run and nothing was billed; signup_url and message say how to fix it.
results_totalNoHow many fares the search selected across every searched combination, before any row bound. Equal to results_returned unless the server bounded a response it had widened itself.
search_statusNoWhether the underlying search actually completed, read from the backend's X-Search-Status header. 'ok': every combination searched returned results. 'empty': the search completed and Google genuinely has no itineraries for it -- a real answer, not a failure. 'partial': some combinations returned results and some failed, so the list is incomplete. 'degraded': every combination failed, so the search did not happen and an empty list means nothing; this case is also flagged with isError: true and is safe to retry. 'trial_exhausted': the free signed-in allowance on this server is spent for today, so nothing was searched and nothing was billed; it renews at 00:00 UTC and connecting your own RapidAPI key removes the cap. Retrying does not help. 'quota_exceeded': the search was refused because the caller's remaining allowance or plan quota cannot cover the number of combinations asked for; combos_requested and combos_allowed_now carry the two numbers. Nothing was searched beyond what it cost to read the quota. Retrying the same search does not help -- ask for fewer dates or nights, or move to a larger plan.
by_destinationNoOne entry per destination the REQUEST asked for, in request order, present whether or not that destination has any flights in `results`. A destination with an empty `rows` array is a hole in the answer, and `reason` says which kind of hole: 'no_flights' (searched, answered, Google has nothing), 'search_failed' (searched and the search errored, so nothing is known), 'not_in_limit' (searched, found flights, none fitted in `limit`) or 'not_searched' (never searched -- the per-call fan-out cap sampled it away). 'ok' means it has rows. Read this rather than inferring coverage from `results`: a destination missing from `results` looks identical to one that has no flights, and they are not the same answer. `row_count` is how many of this destination's fares were selected; the fares themselves are in `results` and are not repeated here. `verbose: true` restores the `rows` array for callers that read it.
quota_exhaustedNoTrue when the caller's RapidAPI plan has no requests left for the current period.
search_coverageNoWhat was actually searched. Present whether or not the request was truncated, so a model can state honestly what its answer rests on.
results_returnedNoHow many of them are in `results` -- the best ones by the sort_by asked for, cheapest first by default, and never all of one destination at the expense of another. Lower than results_total only when `limit` was raised by the server to cover the fan-out rather than asked for; search_coverage.note says so when it happens, and `verbose: true` returns them all.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / passengers / description
      Previous value: -"One entry per traveller, not a count: 1 adult, 2 child (aged 2-11), 3 infant on lap, 4 infant in seat, e.g. [1, 1, 2] for two adults and a child. At least one adult, each infant on lap needs its own adult, at most 9. Omit for one adult."New value: +"One entry per traveller, not a count: 1 adult, 2 child (aged 2-11), 3 infant on lap, 4 infant in seat, e.g. [1, 1, 2] for two adults and a child. At least one adult, each infant on lap needs its own adult, at most 9. Omit for one adult. A counts list [adults, children, infants], e.g. [2, 1, 0], or a bare [2] for two adults, is recognised and converted to codes before the search; a list that is valid as codes is searched as codes."
  2. Changed1 schema field changed
    • changedInput schema / properties / passengers / description
      Previous value: -"Passenger counts as [adults, children, infants]."New value: +"One entry per traveller, not a count: 1 adult, 2 child (aged 2-11), 3 infant on lap, 4 infant in seat, e.g. [1, 1, 2] for two adults and a child. At least one adult, each infant on lap needs its own adult, at most 9. Omit for one adult."
  3. Changed10 schema fields changed
    • addedInput schema / properties / verbose
      Added value: +{
      +  "default": false,
      +  "description": "Return every field the upstream sends on each fare, and every fare that was selected, with no row bound. Off by default: a result carries the best rows by your sort_by in a compact shape (dates, destination, airline, stops, duration, price, trip length and the booking link), because a wide search over a month and several destinations otherwise produces a megabyte of JSON that some hosts refuse to put in the conversation at all. Turn it on when you need the arrival times, the per-leg stop counts, the raw stop details or more rows than results_returned; results_total always says how many there were.",
      +  "type": "boolean"
      +}
    • addedOutput schema / properties / by_destination / additionalProperties / properties / row_count
      Added value: +{
      +  "description": "How many of this destination's fares were selected. Not all of them are necessarily in `results`: a wide search returns the top results_returned of results_total overall, and `cheapest` below is this destination's own best fare either way.",
      +  "minimum": 0,
      +  "type": "integer"
      +}
    • addedOutput schema / properties / by_destination / additionalProperties / properties / rows / description
      Added value: +"Only on `verbose: true`: this destination's selected rows, the same objects that are in `results`."
    • changedOutput schema / properties / by_destination / additionalProperties / required
      Previous value: -[
      -  "rows",
      -  "searched",
      -  "reason"
      -]New value: +[
      +  "row_count",
      +  "searched",
      +  "reason"
      +]
    • changedOutput schema / properties / by_destination / description
      Previous value: -"One entry per destination the REQUEST asked for, in request order, present whether or not that destination has any flights in `results`. A destination with an empty `rows` array is a hole in the answer, and `reason` says which kind of hole: 'no_flights' (searched, answered, Google has nothing), 'search_failed' (searched and the search errored, so nothing is known), 'not_in_limit' (searched, found flights, none fitted in `limit`) or 'not_searched' (never searched -- the per-call fan-out cap sampled it away). 'ok' means it has rows.\n\nRead this rather than inferring coverage from `results`: a destination missing from `results` looks identical to one that has no flights, and they are not the same answer. `rows` are the same row objects that are in `results`, in the same order -- nothing here is data the answer does not already contain."New value: +"One entry per destination the REQUEST asked for, in request order, present whether or not that destination has any flights in `results`. A destination with an empty `rows` array is a hole in the answer, and `reason` says which kind of hole: 'no_flights' (searched, answered, Google has nothing), 'search_failed' (searched and the search errored, so nothing is known), 'not_in_limit' (searched, found flights, none fitted in `limit`) or 'not_searched' (never searched -- the per-call fan-out cap sampled it away). 'ok' means it has rows.\n\nRead this rather than inferring coverage from `results`: a destination missing from `results` looks identical to one that has no flights, and they are not the same answer. `row_count` is how many of this destination's fares were selected; the fares themselves are in `results` and are not repeated here. `verbose: true` restores the `rows` array for callers that read it."
    • addedOutput schema / properties / from_airport
      Added value: +{
      +  "description": "The origin, as the upstream renders it ('Tel Aviv (TLV)'). One origin per search, so it is on the response rather than repeated on every row.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / result_count / description
      Added value: +"How many rows are in `results`; same as results_returned."
    • changedOutput schema / properties / results / description
      Previous value: -"The itineraries or properties found, already sorted and deduplicated. An empty array is only meaningful when search_status is 'empty'."New value: +"The fares found, already sorted and deduplicated. An empty array is only meaningful when search_status is 'empty'.\n\nThis is the TOP results_returned of results_total rows by the sort you asked for -- cheapest first by default, shortest first on sort_by 'duration' -- with every destination that has fares still represented. Each row is in a compact shape: destination, the date or dates, trip length in nights on a round trip, airline (both legs on a round trip), stops, duration, the price as a string and a number, Google's price band with its verdict, and the booking link. The origin is on the response as from_airport rather than repeated on every row. Arrival descriptions, per-leg stop counts, raw stop details and the duration in seconds are dropped; `verbose: true` returns them, and every row that was selected, on that call."
    • addedOutput schema / properties / results_returned
      Added value: +{
      +  "description": "How many of them are in `results` -- the best ones by the sort_by asked for, cheapest first by default, and never all of one destination at the expense of another. Lower than results_total only when `limit` was raised by the server to cover the fan-out rather than asked for; search_coverage.note says so when it happens, and `verbose: true` returns them all.",
      +  "minimum": 0,
      +  "type": "integer"
      +}
    • addedOutput schema / properties / results_total
      Added value: +{
      +  "description": "How many fares the search selected across every searched combination, before any row bound. Equal to results_returned unless the server bounded a response it had widened itself.",
      +  "minimum": 0,
      +  "type": "integer"
      +}
  4. Changed1 schema field changed
    • changedInput schema / properties / max_searches / description
      Previous value: -"The billed requests this call may make, up or down. Leave it out for the normal behaviour: the cap covers the request when the request is reasonable (a whole month at three trip lengths, 93 combinations, runs in full) and anything past it is sampled evenly across the range rather than cut short. Set it lower to spend less of the plan's quota on a wide search, or higher -- to a hard maximum of 200 -- for a grid wider than that."New value: +"The billed requests this call may make, up or down. Leave it out for the normal behaviour: the cap covers the request when the request is reasonable (a whole month at three trip lengths is 93 combinations and a whole month x 3 nights x 3 destinations is 279; both run in full) and anything past it is sampled evenly across the range rather than cut short. Set it lower to spend less of the plan's quota on a wide search, or higher -- to a hard maximum of 300 -- for a grid wider than that."
  5. Changed7 schema fields changed
    • changedInput schema / properties / max_searches / description
      Previous value: -"Cap the billed requests this call may make. Lower it to spend less of the plan's quota on a wide search; the range is then sampled evenly rather than cut short."New value: +"The billed requests this call may make, up or down. Leave it out for the normal behaviour: the cap covers the request when the request is reasonable (a whole month at three trip lengths, 93 combinations, runs in full) and anything past it is sampled evenly across the range rather than cut short. Set it lower to spend less of the plan's quota on a wide search, or higher -- to a hard maximum of 200 -- for a grid wider than that."
    • addedOutput schema / properties / api_usage / properties / hub_requests_billed
      Added value: +{
      +  "description": "How many HTTP requests RapidAPI actually billed. Larger than requests_used_by_this_call when a search failed with a server error and was retried, because the retry is billed too. This is the figure the invoice will show.",
      +  "minimum": 0,
      +  "type": "integer"
      +}
    • addedOutput schema / properties / api_usage / properties / requests_used_by_this_call / description
      Added value: +"How many date/destination combinations were searched -- what the answer COVERS."
    • addedOutput schema / properties / search_coverage / properties / hub_requests_billed
      Added value: +{
      +  "description": "HTTP requests billed by RapidAPI for this call, retries included; see api_usage.hub_requests_billed.",
      +  "minimum": 0,
      +  "type": "integer"
      +}
    • addedOutput schema / properties / search_coverage / properties / stopped_early
      Added value: +{
      +  "description": "Present when something other than the cap ended the fan-out. 'deadline': the call reached its time limit and the remaining combinations were never sent or billed, so the results are real but do not cover the whole range.",
      +  "type": "string"
      +}
    • changedOutput schema / properties / search_status / description
      Previous value: -"Whether the underlying search actually completed, read from the backend's X-Search-Status header. 'ok': every combination searched returned results. 'empty': the search completed and Google genuinely has no itineraries for it -- a real answer, not a failure. 'partial': some combinations returned results and some failed, so the list is incomplete. 'degraded': every combination failed, so the search did not happen and an empty list means nothing; this case is also flagged with isError: true and is safe to retry. 'trial_exhausted': the free signed-in allowance on this server is spent for today, so nothing was searched and nothing was billed; it renews at 00:00 UTC and connecting your own RapidAPI key removes the cap. Retrying does not help."New value: +"Whether the underlying search actually completed, read from the backend's X-Search-Status header. 'ok': every combination searched returned results. 'empty': the search completed and Google genuinely has no itineraries for it -- a real answer, not a failure. 'partial': some combinations returned results and some failed, so the list is incomplete. 'degraded': every combination failed, so the search did not happen and an empty list means nothing; this case is also flagged with isError: true and is safe to retry. 'trial_exhausted': the free signed-in allowance on this server is spent for today, so nothing was searched and nothing was billed; it renews at 00:00 UTC and connecting your own RapidAPI key removes the cap. Retrying does not help. 'quota_exceeded': the search was refused because the caller's remaining allowance or plan quota cannot cover the number of combinations asked for; combos_requested and combos_allowed_now carry the two numbers. Nothing was searched beyond what it cost to read the quota. Retrying the same search does not help -- ask for fewer dates or nights, or move to a larger plan."
    • changedOutput schema / properties / search_status / enum
      Previous value: -[
      -  "ok",
      -  "empty",
      -  "partial",
      -  "degraded",
      -  "trial_exhausted"
      -]New value: +[
      +  "ok",
      +  "empty",
      +  "partial",
      +  "degraded",
      +  "trial_exhausted",
      +  "quota_exceeded"
      +]
  6. Changed2 schema fields changed
    • changedOutput schema / properties / search_status / description
      Previous value: -"Whether the underlying search actually completed, read from the backend's X-Search-Status header. 'ok': every combination searched returned results. 'empty': the search completed and Google genuinely has no itineraries for it -- a real answer, not a failure. 'partial': some combinations returned results and some failed, so the list is incomplete. 'degraded': every combination failed, so the search did not happen and an empty list means nothing; this case is also flagged with isError: true and is safe to retry."New value: +"Whether the underlying search actually completed, read from the backend's X-Search-Status header. 'ok': every combination searched returned results. 'empty': the search completed and Google genuinely has no itineraries for it -- a real answer, not a failure. 'partial': some combinations returned results and some failed, so the list is incomplete. 'degraded': every combination failed, so the search did not happen and an empty list means nothing; this case is also flagged with isError: true and is safe to retry. 'trial_exhausted': the free signed-in allowance on this server is spent for today, so nothing was searched and nothing was billed; it renews at 00:00 UTC and connecting your own RapidAPI key removes the cap. Retrying does not help."
    • changedOutput schema / properties / search_status / enum
      Previous value: -[
      -  "ok",
      -  "empty",
      -  "partial",
      -  "degraded"
      -]New value: +[
      +  "ok",
      +  "empty",
      +  "partial",
      +  "degraded",
      +  "trial_exhausted"
      +]
  7. Changed5 schema fields changed
    • removedOutput schema / properties / by_destination / additionalProperties / properties / cheapest / additionalProperties
      Removed value: -true
    • addedOutput schema / properties / by_destination / additionalProperties / properties / cheapest / anyOf
      Added value: +[
      +  {
      +    "additionalProperties": true,
      +    "type": "object"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • removedOutput schema / properties / by_destination / additionalProperties / properties / cheapest / type
      Removed value: -[
      -  "object",
      -  "null"
      -]
    • addedOutput schema / properties / by_destination / additionalProperties / properties / dates / additionalProperties / properties / cheapest_price / anyOf
      Added value: +[
      +  {
      +    "type": "number"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • removedOutput schema / properties / by_destination / additionalProperties / properties / dates / additionalProperties / properties / cheapest_price / type
      Removed value: -[
      -  "number",
      -  "null"
      -]
  8. Changed1 schema field changed
    • addedOutput schema / properties / by_destination
      Added value: +{
      +  "additionalProperties": {
      +    "additionalProperties": true,
      +    "properties": {
      +      "cheapest": {
      +        "additionalProperties": true,
      +        "description": "The lowest-priced of this destination's rows in `results`, or null when it has none.",
      +        "type": [
      +          "object",
      +          "null"
      +        ]
      +      },
      +      "dates": {
      +        "additionalProperties": {
      +          "additionalProperties": true,
      +          "properties": {
      +            "cheapest_price": {
      +              "type": [
      +                "number",
      +                "null"
      +              ]
      +            },
      +            "reason": {
      +              "enum": [
      +                "ok",
      +                "no_flights",
      +                "search_failed",
      +                "not_in_limit",
      +                "not_searched"
      +              ],
      +              "type": "string"
      +            },
      +            "row_count": {
      +              "minimum": 0,
      +              "type": "integer"
      +            },
      +            "searched": {
      +              "type": "boolean"
      +            }
      +          },
      +          "type": "object"
      +        },
      +        "description": "Present only on multi-date searches: one entry per departure date requested for this destination, so a date the fan-out cap sampled away is visible rather than absent. `cheapest_price` is null when that date has no row in `results`.",
      +        "type": "object"
      +      },
      +      "reason": {
      +        "enum": [
      +          "ok",
      +          "no_flights",
      +          "search_failed",
      +          "not_in_limit",
      +          "not_searched"
      +        ],
      +        "type": "string"
      +      },
      +      "rows": {
      +        "items": {
      +          "additionalProperties": true,
      +          "type": "object"
      +        },
      +        "type": "array"
      +      },
      +      "searched": {
      +        "description": "Whether at least one search actually ran for this destination. False means the fan-out cap dropped it.",
      +        "type": "boolean"
      +      }
      +    },
      +    "required": [
      +      "rows",
      +      "searched",
      +      "reason"
      +    ],
      +    "type": "object"
      +  },
      +  "description": "One entry per destination the REQUEST asked for, in request order, present whether or not that destination has any flights in `results`. A destination with an empty `rows` array is a hole in the answer, and `reason` says which kind of hole: 'no_flights' (searched, answered, Google has nothing), 'search_failed' (searched and the search errored, so nothing is known), 'not_in_limit' (searched, found flights, none fitted in `limit`) or 'not_searched' (never searched -- the per-call fan-out cap sampled it away). 'ok' means it has rows.\n\nRead this rather than inferring coverage from `results`: a destination missing from `results` looks identical to one that has no flights, and they are not the same answer. `rows` are the same row objects that are in `results`, in the same order -- nothing here is data the answer does not already contain.",
      +  "type": "object"
      +}
  9. Changed2 schema fields changed
    • changedInput schema / properties / from_airport / description
      Previous value: -"Origin IATA code, e.g. \"TLV\"."New value: +"Origin IATA code, e.g. \"TLV\". One origin per search; a second one is refused rather than searched."
    • changedInput schema / properties / to_airport / description
      Previous value: -"Destination IATA code, or a list of them to compare."New value: +"Destination airport. One IATA code (\"BCN\"), several separated by commas (\"BCN,LIS,ATH\"), or a list ([\"BCN\",\"LIS\",\"ATH\"]) -- every shape is accepted and the destinations are compared in the same search."
  10. Changed4 schema fields changed
    • addedOutput schema / description
      Added value: +"A completed flight search. Read search_status before reading results: an empty array means 'no flights' only when search_status is 'empty'."
    • addedOutput schema / properties
      Added value: +{
      +  "api_usage": {
      +    "additionalProperties": true,
      +    "description": "What this call cost the caller's own RapidAPI plan, and what remains on it. Present on every response that reached the upstream, including a degraded one -- a search that failed was still billed.",
      +    "properties": {
      +      "note": {
      +        "description": "The same figures as a sentence, for the model to relay.",
      +        "type": "string"
      +      },
      +      "plan_requests_limit": {
      +        "type": "integer"
      +      },
      +      "plan_requests_remaining": {
      +        "type": "integer"
      +      },
      +      "requests_used_by_this_call": {
      +        "minimum": 0,
      +        "type": "integer"
      +      }
      +    },
      +    "type": "object"
      +  },
      +  "message": {
      +    "description": "Present when there is something the model must relay to the user rather than silently absorb -- no results, a degraded search, a missing key or a spent quota.",
      +    "type": "string"
      +  },
      +  "needs_api_key": {
      +    "description": "True when no usable RapidAPI key arrived with the call, or the upstream rejected the one that did. No search was run and nothing was billed; signup_url and message say how to fix it.",
      +    "type": "boolean"
      +  },
      +  "partial": {
      +    "description": "Present when some searches failed but others succeeded. Plain text saying how much of the request the results cover.",
      +    "type": "string"
      +  },
      +  "quota_exhausted": {
      +    "description": "True when the caller's RapidAPI plan has no requests left for the current period.",
      +    "type": "boolean"
      +  },
      +  "result_count": {
      +    "minimum": 0,
      +    "type": "integer"
      +  },
      +  "results": {
      +    "description": "The itineraries or properties found, already sorted and deduplicated. An empty array is only meaningful when search_status is 'empty'.",
      +    "items": {
      +      "additionalProperties": true,
      +      "type": "object"
      +    },
      +    "type": "array"
      +  },
      +  "search_coverage": {
      +    "additionalProperties": true,
      +    "description": "What was actually searched. Present whether or not the request was truncated, so a model can state honestly what its answer rests on.",
      +    "properties": {
      +      "departure_dates_searched": {
      +        "items": {
      +          "type": "string"
      +        },
      +        "type": "array"
      +      },
      +      "destinations_searched": {
      +        "items": {
      +          "type": "string"
      +        },
      +        "type": "array"
      +      },
      +      "max_searches_per_request": {
      +        "minimum": 1,
      +        "type": "integer"
      +      },
      +      "note": {
      +        "type": "string"
      +      },
      +      "requested_combinations": {
      +        "minimum": 0,
      +        "type": "integer"
      +      },
      +      "searched_combinations": {
      +        "minimum": 0,
      +        "type": "integer"
      +      },
      +      "truncated": {
      +        "description": "True when the request expanded past this call's spend ceiling and was sampled. A date absent from departure_dates_searched was never searched, which is not the same as having no flights.",
      +        "type": "boolean"
      +      }
      +    },
      +    "type": "object"
      +  },
      +  "search_status": {
      +    "description": "Whether the underlying search actually completed, read from the backend's X-Search-Status header. 'ok': every combination searched returned results. 'empty': the search completed and Google genuinely has no itineraries for it -- a real answer, not a failure. 'partial': some combinations returned results and some failed, so the list is incomplete. 'degraded': every combination failed, so the search did not happen and an empty list means nothing; this case is also flagged with isError: true and is safe to retry.",
      +    "enum": [
      +      "ok",
      +      "empty",
      +      "partial",
      +      "degraded"
      +    ],
      +    "type": "string"
      +  },
      +  "signup_url": {
      +    "description": "Where the caller subscribes or changes plan.",
      +    "type": "string"
      +  }
      +}
    • addedOutput schema / required
      Added value: +[
      +  "results"
      +]
    • addedOutput schema / title
      Added value: +"Flight search result"
  11. Changed22 schema fields changed
    • addedInput schema / properties / currency / description
      Added value: +"ISO currency code, default \"usd\"."
    • addedInput schema / properties / departure_airline_codes / description
      Added value: +"Restrict the outbound leg to these airlines."
    • addedInput schema / properties / departure_date / description
      Added value: +"Single outbound date, \"YYYY-MM-DD\"."
    • addedInput schema / properties / departure_date_from / description
      Added value: +"First date of an outbound range."
    • addedInput schema / properties / departure_date_to / description
      Added value: +"Last date of an outbound range."
    • addedInput schema / properties / from_airport / description
      Added value: +"Origin IATA code, e.g. \"TLV\"."
    • addedInput schema / properties / limit / description
      Added value: +"Maximum trips to return, after merging and sorting."
    • addedInput schema / properties / max_departure_stops / description
      Added value: +"Maximum stops on the outbound leg."
    • addedInput schema / properties / max_price / description
      Added value: +"Only return trips at or below this total price."
    • addedInput schema / properties / max_return_stops / description
      Added value: +"Maximum stops on the return leg."
    • addedInput schema / properties / max_searches / description
      Added value: +"Cap the billed requests this call may make. Lower it to spend less of the plan's quota on a wide search; the range is then sampled evenly rather than cut short."
    • addedInput schema / properties / nights / description
      Added value: +"Trip length in nights; a number, or a list like [5, 6, 7]. The return date is derived from each departure date."
    • addedInput schema / properties / passengers / description
      Added value: +"Passenger counts as [adults, children, infants]."
    • addedInput schema / properties / return_airline_codes / description
      Added value: +"Restrict the return leg to these airlines."
    • addedInput schema / properties / return_date / description
      Added value: +"Fixed return date. Use this OR nights, not both."
    • addedInput schema / properties / seat_type / description
      Added value: +"1 economy, 2 premium economy, 3 business, 4 first."
    • addedInput schema / properties / sort_by / description
      Added value: +"\"best\", \"price\", or \"duration\". Applied across all results."
    • addedInput schema / properties / to_airport / description
      Added value: +"Destination IATA code, or a list of them to compare."
    • addedInput schema / properties / use_fallback / anyOf
      Added value: +[
      +  {
      +    "type": "boolean"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / properties / use_fallback / default
      Previous value: -falseNew value: +null
    • addedInput schema / properties / use_fallback / description
      Added value: +"Leave unset. Switches the search to a second, independent flight data source instead of the usual Google Flights page read. Unset already escalates to that source once, automatically, after a search's retries have failed. true forces it inline on every attempt -- much slower, and it can time out. false disables it entirely, that automatic retry included."
    • removedInput schema / properties / use_fallback / type
      Removed value: -"boolean"
  12. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations (readOnlyHint, openWorldHint, idempotentHint=false, destructiveHint=false) already carry the safety profile, and the description goes well beyond them: every date/night/destination combination is a separately billed request, retries are billed, the true cost figure is api_usage.hub_requests_billed, usage counts against the caller's own RapidAPI plan, and by_destination includes empty entries with a reason. Auth requirements and the fallback data source behaviour are also disclosed.

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?

The purpose is front-loaded in the first sentence and the body is organized into scannable units (usage, cost, response shape, auth). It is long and the RapidAPI sign-up/onboarding paragraph is the least essential part, costing it a point, but nearly every section carries operational information an agent would otherwise have to guess.

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?

For a 20-parameter tool with an output schema, the description covers what an agent needs to call it correctly: date/nights mechanics, destination list shapes, billing and quota accounting, the meaning of by_destination, and when verbose is required. It even explains the response envelope fields (api_usage, results_total) despite the output schema existing.

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%, so the per-field docs already carry most meaning (baseline 3), but the description adds genuine value about how fields combine: departure_date_from/to plus nights replaces return_date for a flexible search, multi-code destinations are compared in one search, and the combination math that drives how many requests a call will spend. It does not restate the enum-style field semantics that the schema already explains.

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 gives a precise verb+resource (round-trip fare search) and a scoping detail that separates it from its sibling: fares are 'priced as paired legs rather than two separate one-ways', which is exactly what distinguishes it from search_oneway_flights. An agent can route between the two tools without opening either 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 explicitly says 'Use it for any return-trip fare question' and then gives concrete calling rules: make ONE call with departure_date_from/to plus nights for a flexible search, a whole month is one call, and 'do not split it into several calls'. It also states when to warn the user about billed volume before running a large search.

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.