Skip to main content
Glama

Search flights by route

search_flights
Read-onlyIdempotent

Today's departures from an airport still to leave (airport-local day), optionally only those to one destination or flown by one airline: finds flights without knowing their number. Each flight has its number, operating flight for codeshares, destination, scheduled and actual departure in UTC, status, delay, a link to its flight page and, when one is open, to its market; with counts of matching flights departed and still to depart.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

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

Input Schema

NameRequiredDescriptionDefault
toNoDestination airport IATA or ICAO code, or city name (e.g. JFK, KJFK or New York).
fromYesDeparture airport. Airport IATA code (e.g. LHR) or ICAO code (e.g. EGLL).
limitNoMax flights to return (1-50). Defaults to 20.
airlineNoAirline IATA or ICAO code (e.g. BA or BAW).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the description's added value is the semantics: the day window is airport-local and excludes already-departed flights, and results include a departed/still-to-depart count. That is genuine behavioral context beyond the annotations, though it says nothing about pagination limits or ordering of results.

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 core capability and time window are front-loaded in the first clause, with the return payload following. It is dense and slightly run-on in the second clause, but nearly every phrase carries information the agent needs.

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?

With no output schema, the description compensates by enumerating the returned fields (number, operating flight for codeshares, destination, scheduled/actual departure in UTC, status, delay, links, counts). Combined with the defined time window and optional filters, an agent has enough to invoke and interpret the tool correctly.

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 100%, so each parameter (from, to, airline, limit) is already documented with formats and examples. The description adds only the framing that to/airline are optional narrowing filters; it contributes no detail on limit behavior or combining filters, so the baseline 3 applies.

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 a specific resource ('Today's departures from an airport still to leave') and a concrete capability ('finds flights without knowing their number'), which implicitly separates it from flight-number lookup siblings like get_flight_status. Scope (airport-local day, still-to-depart only) is stated up front, so an agent can tell what this tool does 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?

Usage context is clear: use this when you don't have a flight number, for today's not-yet-departed flights from a given airport, optionally narrowed by destination or airline. It lacks an explicit negative clause naming the alternative tool for departed/past flights (e.g. history), so it stops short of full when/when-not guidance.

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