SlickTrip

Search flights

search_flights

Read-onlyIdempotent

Use when the traveler wants flights for known dates: one way, round trip, flexible dates, several airports, or multi-city. Give origin, destination and depart_date (return_date for a round trip), or pass their own words in query and leave unknown fields empty (nothing is guessed), or legs for multi-city. Returns priced itineraries cheapest first, itinerary_ids for track_flight and search_return_flights, and a search_url. Not for 'when is it cheapest' (price_calendar) or flexible months (add_flight_bucket_list).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`legs`	No	Multi-city trip: the legs in order, 2 to 5, each one airport or city code per side and one date. When given, origin / destination / depart_date / return_date are ignored.
`sort`	No	Order of results.	price
`cabin`	No	Cabin class.	economy
`query`	No	The traveler's request in their own words, used to fill any field left empty.
`origin`	No	A 3-letter airport code (JFK) or a city code for all its airports (NYCA, LOND, ROME); up to 3 joined with _ (JFK_EWR). A clear place name works too. Unsure of the code: call find_places.
`airlines`	No	Only these marketing carriers, as IATA codes or names.
`max_stops`	No	Most stops allowed: 0 nonstop, 1, or 2.
`travelers`	No	Travelers. Fares are quoted for all of them together; one booking holds up to 9 (a larger group gets a suggested split).
`depart_date`	No	YYYY-MM-DD. A second date joined with _ searches both as flexible dates (2026-11-03_2026-11-04); at most 2 per direction.
`destination`	No	A 3-letter airport code (JFK) or a city code for all its airports (NYCA, LOND, ROME); up to 3 joined with _ (JFK_EWR). A clear place name works too. Unsure of the code: call find_places.
`max_results`	No	How many results to return, 1-50.
`return_date`	No	YYYY-MM-DD for a round trip; empty for one way.
`arrive_after`	No	HH:MM, local time at that airport.
`depart_after`	No	HH:MM, local time at that airport.
`user_request`	No	Optional. The traveler's current travel request, briefly, in their own words. Used to interpret this search, suggest a corrected search if it fails, and improve SlickTrip's search. Include only this request; not earlier conversation, names, contact details, or payment or ID information.
`arrive_before`	No	HH:MM, local time at that airport.
`depart_before`	No	HH:MM, local time at that airport.
`max_price_usd`	No	Highest fare to show, USD, as the TOTAL for all travelers together: for a per-person budget, multiply by travelers (2 people at $300 each = 600). Unlike bucket lists, whose price bar is per traveler.
`max_duration_hours`	No	Longest itinerary to show, in hours.

Output Schema

TableJSON Schema

Name	Required	Description
`code`	No	On an error: a machine-readable kind, e.g. unknown_place
`note`	No	Guidance on trip type or why empty
`field`	No	On unknown_place: which argument (origin, destination, ...)
`counts`	No	priced, matching_filters, returned integers
`search`	No	Route dict: origin, destination, names, destination_image, cabin, travelers, dates, trip_type, legs (multi-city), search_key, served_from, retrieved_at
`status`	No	ok \| no_data \| error \| sign_in_required
`filters`	No	Filters as the caller gave them (max_stops, airlines, max_price_usd, ...)
`message`	No	Error or sign-in message from the server wrapper
`highlights`	No	The spread over every matching fare: cheapest, cheapest_nonstop, fastest, earliest, latest; each with itinerary_id, price, airlines, stops, duration_minutes, departs_at
`search_url`	No	slicktrip.com search page link with attribution
`itineraries`	No	Items: itinerary_id, price {total_usd, per_traveler_usd}, outbound leg, needs_leg, track_url, optional depart_date + search_key
`searched_as`	No	What the search assumed: trip type, travelers, cabin
`suggestions`	No	On unknown_place: places to offer the traveler, each with code, name, kind (airport, all airports in the city, nearby airport), city, country
`places_assumed`	No	Place names this call resolved on its own, e.g. 'Portland = Portland, OR (PDX)'; tell the traveler

Schema Changelog

Changes observed during successful MCP inspections.

Changed8 schema fields changedOct 6, 2026

changedInput schema / $defs / Leg / properties / destination / description

Previous value: -"A 3-letter airport code (JFK), or a city code that searches every airport in the city (NYC, LON, ROM, TYO). Up to 3 airports joined with _ search them together (JFK_EWR). A place name works when one place clearly matches; otherwise the result is an unknown_place error listing suggestions. Unsure of the code: call find_places."New value: +"A 3-letter airport code (JFK), or a city code that searches every airport in the city (SlickTrip's 4-letter codes: NYCA New York, LOND London, ROME Rome, TYOA Tokyo). Up to 3 places joined with _ search them together (JFK_EWR). A place name works when one place clearly matches; otherwise the result is an unknown_place error listing suggestions. Unsure of the code: call find_places."

changedInput schema / $defs / Leg / properties / destination / examples

Previous value: -[
-  "JFK",
-  "ROM",
-  "JFK_EWR"
-]New value: +[
+  "JFK",
+  "NYCA",
+  "JFK_EWR"
+]

changedInput schema / $defs / Leg / properties / origin / description

Previous value: -"A 3-letter airport code (JFK), or a city code that searches every airport in the city (NYC, LON, ROM, TYO). Up to 3 airports joined with _ search them together (JFK_EWR). A place name works when one place clearly matches; otherwise the result is an unknown_place error listing suggestions. Unsure of the code: call find_places."New value: +"A 3-letter airport code (JFK), or a city code that searches every airport in the city (SlickTrip's 4-letter codes: NYCA New York, LOND London, ROME Rome, TYOA Tokyo). Up to 3 places joined with _ search them together (JFK_EWR). A place name works when one place clearly matches; otherwise the result is an unknown_place error listing suggestions. Unsure of the code: call find_places."

changedInput schema / $defs / Leg / properties / origin / examples

Previous value: -[
-  "JFK",
-  "ROM",
-  "JFK_EWR"
-]New value: +[
+  "JFK",
+  "NYCA",
+  "JFK_EWR"
+]

changedInput schema / properties / destination / description

Previous value: -"A 3-letter airport code (JFK) or a city code for all its airports (NYC, LON, ROM); up to 3 joined with _ (JFK_EWR). A clear place name works too. Unsure of the code: call find_places."New value: +"A 3-letter airport code (JFK) or a city code for all its airports (NYCA, LOND, ROME); up to 3 joined with _ (JFK_EWR). A clear place name works too. Unsure of the code: call find_places."

changedInput schema / properties / destination / examples

Previous value: -[
-  "JFK",
-  "ROM",
-  "JFK_EWR"
-]New value: +[
+  "JFK",
+  "NYCA",
+  "JFK_EWR"
+]

changedInput schema / properties / origin / description

Previous value: -"A 3-letter airport code (JFK) or a city code for all its airports (NYC, LON, ROM); up to 3 joined with _ (JFK_EWR). A clear place name works too. Unsure of the code: call find_places."New value: +"A 3-letter airport code (JFK) or a city code for all its airports (NYCA, LOND, ROME); up to 3 joined with _ (JFK_EWR). A clear place name works too. Unsure of the code: call find_places."

changedInput schema / properties / origin / examples

Previous value: -[
-  "JFK",
-  "ROM",
-  "JFK_EWR"
-]New value: +[
+  "JFK",
+  "NYCA",
+  "JFK_EWR"
+]

First observedOct 5, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so safety is covered. The description still adds real behavioral context: results come back priced cheapest-first, include itinerary_ids consumed by track_flight/search_return_flights and a search_url, and that unknown fields are left empty because 'nothing is guessed'. It stops short of covering pagination or error/empty-result behavior, so not a 5.

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?

Two dense sentences, front-loaded with the usage trigger and ending with the exclusion clause; every clause carries information. It is long but not padded given 19 parameters and multiple modes, though the middle 'or ... or ...' construction takes some parsing.

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 19-parameter, multi-mode search tool with full schema coverage, output schema present, and rich annotations, the description covers the remaining gaps: mode selection, field-population strategy, override precedence, and the return artifact (itinerary_ids, search_url). Nothing an agent needs to call it correctly is missing.

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 baseline is 3, but the description adds cross-parameter semantics the schema does not: legs overrides origin/destination/dates, and query backfills any empty field while unknown fields stay empty. These interaction rules are genuinely beyond the per-field schema text.

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 description names the specific verb and resource and enumerates the callable modes (one way, round trip, flexible dates, several airports, multi-city). It also explicitly marks the sibling tools it is not (price_calendar, add_flight_bucket_list), so an agent can distinguish it without opening the 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 opens with an explicit 'Use when the traveler wants flights for known dates' trigger, describes how to populate fields for each mode, and closes with explicit exclusions routing to price_calendar and add_flight_bucket_list. This is when-to-use plus when-not-to-use plus named alternatives.

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

All SlickTrip 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?