Skip to main content
Glama

Get fare family

get_fare_family
Read-onlyIdempotent

Fare family / branded fare selector for ONE specific flight. Returns every fare the airline sells on that flight (Saver, Flexi, Flexi Plus, ...) with a single recommended pick and the reasons for it, scored on concrete rupee benefit per rupee of premium. It answers which fare to pick, fare families, branded fares, fare types, 'what do I get for more', or a comparison of fare options for a flight already chosen, typically straight after search_flights or when the traveller taps the fare CTA in the results widget. Policy detail (baggage, cancellation, reschedule) comes from get_flight_details instead. Input: that flight's offer_token from search_flights (plus return_offer_token for a round trip). TWO FORMS ARE VALID and the tool accepts either: the long signed token, or the SHORT REFERENCE from the same flight's offerRef field (about 30 characters, e.g. 'AkJMUkRFTGUJAABFEAAhRs3JWXw'). A short value is NOT a mistake and not an internal id: the widget's Book action deliberately passes the short form so a 400-character token stays out of the conversation, and it goes in as offer_token as given. Values are matched exactly, character for character: a retyped, abbreviated or merged value fails, the onward value is not valid for the return leg, and a round trip needs BOTH. They expire; a rejected value needs a fresh search_flights, not an old value. The selector's Continue (or a request to review / book the fare on screen) leads to get_flight_review: that follow-up arrives as a new user turn naming the offer_token and the selected fare's price, which are exactly get_flight_review's arguments, so the review page renders as its own card. The identifiers in hand are enough without a new search. One result covers every fare on that flight, so later questions about that flight's fares are answerable from it. A repeat call for the same flight re-renders the same widget above the answer; only a different flight needs a new call.

Input Schema

NameRequiredDescriptionDefault
offer_tokenYesOffer token from search_flights — either the long signed token or the flight's short `offerRef`. Both resolve to the same offer.
return_offer_tokenNoOptional return-leg token for a round trip, in either of the same two forms.

Output Schema

NameRequiredDescriptionDefault
legsNo
cabinNo
faresNo
originNo
headingNo
currencyNoINR
tripTypeNoone_way
fareCountNo
requestIdNo
offerTokenNo
solutionIdNo
compareRowsNo
destinationNo
flightNumberNo
pairBookingUrlsNo
recommendedFareNo
recommendedIndexNo
returnOfferTokenNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / offer_token / description
      Previous value: -"Offer token from search_flights — either the long signed\ntoken or the flight's short `offerRef`. Both resolve to the same\noffer; the widget's Book action sends the short form so a\n400-character token never travels through the conversation."New value: +"Offer token from search_flights — either the long signed\ntoken or the flight's short `offerRef`. Both resolve to the same\noffer."
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations give read-only/idempotent/openWorld=false, and the description layers on traits those annotations cannot express: token expiry, exact character-for-character matching, that a retyped or merged value fails, that a short offerRef is legitimate rather than an error or internal id, that a round trip requires BOTH tokens, and that errors require a fresh search_flights. This is materially more than the structured fields provide.

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 the two accepted token forms are front-loaded, and most sentences carry non-obvious operational detail. It is long for a two-parameter tool and has some redundancy, re-explaining the short-token rationale in two separate places, but it avoids boilerplate and every paragraph adds usable guidance.

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, so return-shape explanation is not owed. The description covers the remaining agent-facing gaps: how to obtain and pass the input, error/expiry recovery, the handoff to get_flight_review with the exact argument mapping, and that one result answers later fare questions about that flight.

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 both properties already document the long-token/short-offerRef duality, so the baseline is 3. The description still adds operational meaning the schema does not: the short form is deliberate widget behavior (not a mistake), values are matched exactly, and return_offer_token is mandatory for round trips even though the schema marks it optional with an empty default.

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 first sentence names a concrete verb and scope ('Fare family / branded fare selector for ONE specific flight') and the description enumerates the exact user phrasings it answers (fare families, branded fares, 'what do I get for more'). It explicitly contrasts itself with get_flight_details (policy detail) and get_flight_review (continuation), so an agent can separate it from siblings without opening a 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?

Timing is stated precisely: 'typically straight after search_flights or when the traveller taps the fare CTA in the results widget', with a named exclusion ('Policy detail ... comes from get_flight_details instead') and a named follow-on ('Continue ... leads to get_flight_review'). It also says when NOT to re-call: 'A repeat call for the same flight re-renders the same widget ... only a different flight needs a new call.'

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