Skip to main content
Glama

SlickTrip

by com.slicktrip
OverviewDiscussionsAdmin

Track seats on a flight

track_seats
Idempotent

Use to start seat alerts on one flight, after the traveler confirms: named seats, or every seat of a kind (window, aisle, middle, any), optionally only when N seats open together in a row. Alerts go to the account's channels when a watched seat opens.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
textNoSend alerts by text message. Needs a verified phone on the SlickTrip account; empty keeps the account's setting.
cabinNoCabin to look at; any = every cabin on the flight.economy
emailNoSend alerts by email. Empty keeps the account's setting.
seatsNoSeat numbers to watch.
originYesA 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.
seat_typeNoWatch every open seat of this kind instead of naming seats.
depart_dateYesYYYY-MM-DD.
destinationYesA 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.
flight_numberYesAirline code and number, no space.
seats_togetherNoAlert only when this many seats are open together in one row, 2-6.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
codeNoOn an error: a machine-readable kind, e.g. unknown_place
noteNoManage on saved-seats page
cabinNoCabin tracked, or list when several
fieldNoOn unknown_place: which argument (origin, destination, ...)
alertsNoPlain-words description of alerts
flightNoflight_number, origin, destination, departure_time, arrival_time, aircraft, airline
statusNotracking | error | sign_in_required
messageNoError or sign-in message from the server wrapper
trackedNoseats, seat_type, specific_seats, seats_together, open_now
channelsNoAlert channels on the record: email, text (booleans)
saved_urlNoslicktrip.com saved-seats page link
suggestionsNoOn unknown_place: places to offer the traveler, each with code, name, kind (airport, all airports in the city, nearby airport), city, country
tracking_keyNoSeat tracking key: route;departure_time;flight_number
places_assumedNoPlace names this call resolved on its own, e.g. 'Portland = Portland, OR (PDX)'; tell the traveler
merged_with_existingNoAdded to an existing seat alert

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / 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 / 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 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 / properties / origin / examples
      Previous value: -[
-  "JFK",
-  "ROM",
-  "JFK_EWR"
-]New value: +[
+  "JFK",
+  "NYCA",
+  "JFK_EWR"
+]
  2. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, and openWorldHint=true, so the safety and idempotency profile is covered. The description adds genuine context beyond that: alerts are delivered to the account's channels when a watched seat opens, which tells the agent what the tool actually does over time.

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 sentences, front-loaded with the action and purpose. The first sentence is long but each clause (modes, seats_together option) carries information; the second earns its place by describing alert delivery. No padding.

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 a ten-parameter tracking-creation tool with an output schema, the description covers the action, the confirmation precondition, the seat-selection modes, and the alert behavior. Return values need not be described since an output schema exists. Minor gap: no explicit relationship to sibling tracking tools.

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?

Schema description coverage is 100%, so the schema already documents all ten parameters including seat naming, seat_type, and seats_together. The description restates seats/seat_type/seats_together in prose but adds no syntax or format detail beyond the schema, so the baseline 3 applies.

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 specific verb and resource: 'start seat alerts on one flight,' which distinguishes creation from stop_tracking_seats and update_seat_tracking by the word 'start.' It does not name a sibling explicitly, so it falls short of the 5 reserved for explicit sibling differentiation.

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

Usage Guidelines3/5

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

It gives an explicit precondition ('after the traveler confirms') and describes the two watch modes (named seats vs seat type), which is clear context. However, it never routes the agent away from seat_availability or toward update_seat_tracking, and offers no when-not guidance, so the usage story remains implied rather than complete.

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

All SlickTrip toolsInspect
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