Skip to main content
Glama

Find Direct Flights to a Destination

search_flights
Read-only

Direct flights observed landing at the airports that serve a place over the latest season, one row per origin and destination airport with every airline on that pair folded together. It names no airline and no price and is not a timetable or a booking: a row shows that passenger airlines' aircraft land there on that pattern, not that a seat is for sale. It covers direct flights only: when none comes from the guest's origin, say that connecting flights through other airports may exist and are not listed here. airports are the airports the place is served by, best first. For one place they carry drive_minutes and drive_km by car where known; for an area there is no drive time, because it differs per place (get_location_details gives it per place). ferry true means the drive crosses by ferry; when any airport you give has it, say once that ferries run on schedules and some are seasonal, so the guest checks the crossing before booking flights. Per flight: from/from_name the origin airport, to the destination, weekdays the days it lands, arrivals the landing times in local time at the destination, km the distance between the two airports. year_round true means all year; otherwise season_start is the first landing of the season, season_end the last landing if the route had stopped, and season_end_last_year the date it stopped the year before. A date that is absent is not known; never state one. total_matching counts all flights; the rows are the first limit, in the order of airports, then most flown. Which airport to fly into for a place comes from get_location_details; call this tool with from when the guest asks about flights from a place.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_flights"
  }
}

Input Schema

NameRequiredDescriptionDefault
fromNoThe guest's departure: the ICAO codes of every airport serving their departure city, comma-separated (resolve a city or an IATA code to ICAO yourself). Only flights from those airports are returned, by the order of `airports`, then most flown; when none match, the list is empty, never flights from another origin.
limitNo
locationNoPlace the guest wants to reach, as the guest says it. Resolved to a real place; if it resolves to nothing you get `location_unresolved` and no flights, never flights somewhere else.
location_idNoLocation id from an earlier search_locations or get_location_details result, used instead of `location`.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior5/5

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

Annotations only declare a safe read, but the description adds substantial behavior: results are observational season data rather than availability, unknown dates must never be stated, `total_matching` versus the `limit` truncation and its ordering, the ferry caveat that must be surfaced once to the guest, and the fact that drive times are absent for areas. These are guest-facing obligations an agent could not infer from the readOnly/openWorld annotations.

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 and the not-a-booking caveat are front-loaded, and virtually every clause carries operational meaning (season fields, unknown dates, ferry warning). It is a dense single block, however, and much of the middle is return-field documentation that reads as a data dictionary rather than guidance, which costs it some scannability.

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?

There is no output schema, so the description must document the return shape, and it does so exhaustively: airports with drive_minutes/drive_km, ferry, and per-flight from/to/weekdays/arrivals/km/year_round/season dates, plus total_matching and truncation. For a read-only, four-parameter search with annotations covering safety, nothing an agent needs to call it or report results correctly appears to be 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?

Schema coverage is 75%, so `from`, `location` and `location_id` already carry most of their meaning in structured fields. The description adds the ordering rule tied to `from` ('in the order of `airports`, then most flown') and the instruction to pass `from` when the guest asks about departures, but says nothing about `limit` or the default of 5 beyond the schema. This is the baseline case where the schema does the heavy lifting.

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 states a specific verb and resource ('Direct flights observed landing at the airports that serve a place over the latest season') plus the row grain ('one row per origin and destination airport with every airline on that pair folded together'). It then explicitly fences off what it is not — 'not a timetable or a booking' — and that rows show observed landings, not sellable seats, so an agent can distinguish it from a booking or schedule tool 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 Guidelines4/5

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

It gives a clear activation condition ('call this tool with `from` when the guest asks about flights from a place') and an explicit negative case: when nothing comes from the guest's origin, say connecting flights may exist and are not listed here. It also routes to get_location_details for deciding which airport to fly into. It stops short of naming a sibling as a substitute for the flight-search itself, so it is strong context rather than a full when/when-not/alternative map.

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.