Skip to main content
Glama

Weekend round-trip prices for one route

weekend_prices

Every weekend of the next 12 months for one origin-destination pair, with the cheapest round-trip price per weekend Prices answer at once; weekends not priced yet are searched live during the call, the way a page visit searches them (usually 10-40 s, at most ~55 s). If the search does not finish, the answer says which weekends are still open and to call again. Takes every filter the route page has: trip shape (combo), cabin, stops, passengers, departure and return time windows, currency. Free: fri-sun, economy, any stops, any passenger mix, no time window. Pro session cookie: other combos, other cabins, time windows.

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": {
      "origin": "<origin>",
      "dest": "<dest>"
    },
    "name": "weekend_prices"
  }
}

Input Schema

NameRequiredDescriptionDefault
destYesArrival airport IATA code, e.g. "BCN".
cabinNoDefault "economy" (free). Other cabins need a Pro session cookie.
comboNoTrip shape: out day and back day as "{out}-{back}" with 3-letter days ("tue-thu"); the same day twice is a day trip. Default "fri-sun" (free). Other shapes need a Pro session cookie.
stopsNo"any" (default) or "nonstop". Free.
adultsNoDefault 1. Free. At most 9 travellers in total.
originYesDeparture airport IATA code, e.g. "ZRH".
out_toNoLatest outbound departure, "HH:MM". Pro.
ret_toNoLatest return departure, "HH:MM". Pro.
infantsNoUnder 2. Default 0. Free.
childrenNoAges 2-11. Default 0. Free.
currencyNoISO 4217 code. Default: the native currency of the origin (ZRH → CHF, BCN → EUR).
out_fromNoEarliest outbound departure, "HH:MM" local. Pro. Cached only for weekends whose flight detail is stored.
ret_fromNoEarliest return departure, "HH:MM". Pro.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / combo / description
      Previous value: -"Weekend shape: out day and back day. Default \"fri-sun\" (free). Other shapes need a Pro session cookie."New value: +"Trip shape: out day and back day as \"{out}-{back}\" with 3-letter days (\"tue-thu\"); the same day twice is a day trip. Default \"fri-sun\" (free). Other shapes need a Pro session cookie."
    • changedInput schema / properties / combo / enum
      Previous value: -[
      -  "thu-sun",
      -  "thu-mon",
      -  "thu-sat",
      -  "fri-sun",
      -  "fri-mon",
      -  "fri-sat",
      -  "sat-mon",
      -  "sat-sun",
      -  "sat-sat"
      -]New value: +[
      +  "mon-mon",
      +  "mon-tue",
      +  "mon-wed",
      +  "mon-thu",
      +  "mon-fri",
      +  "mon-sat",
      +  "mon-sun",
      +  "tue-tue",
      +  "tue-wed",
      +  "tue-thu",
      +  "tue-fri",
      +  "tue-sat",
      +  "tue-sun",
      +  "tue-mon",
      +  "wed-wed",
      +  "wed-thu",
      +  "wed-fri",
      +  "wed-sat",
      +  "wed-sun",
      +  "wed-mon",
      +  "wed-tue",
      +  "thu-thu",
      +  "thu-fri",
      +  "thu-sat",
      +  "thu-sun",
      +  "thu-mon",
      +  "thu-tue",
      +  "thu-wed",
      +  "fri-fri",
      +  "fri-sat",
      +  "fri-sun",
      +  "fri-mon",
      +  "fri-tue",
      +  "fri-wed",
      +  "fri-thu",
      +  "sat-sat",
      +  "sat-sun",
      +  "sat-mon",
      +  "sat-tue",
      +  "sat-wed",
      +  "sat-thu",
      +  "sat-fri",
      +  "sun-sun",
      +  "sun-mon",
      +  "sun-tue",
      +  "sun-wed",
      +  "sun-thu",
      +  "sun-fri",
      +  "sun-sat"
      +]
  2. First observed

TDQS

A4.1/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so well: it discloses latency (10-40s, up to ~55s), that cached weekends return instantly while others are searched live during the call, that partial results name the still-open weekends and instruct a retry, and what auth tier each filter requires. That is exactly the behavioral context an agent needs before invoking a slow call.

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?

Front-loaded with scope, then latency, then failure behavior, then filter tiers — a sensible order. A few phrases are awkward ('Prices answer at once', 'Takes every filter the route page has'), but nothing is padded.

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 13-parameter, no-annotation, no-output-schema tool, the description covers timing, partial results, retry behavior and access tiers. Remaining gaps are modest: it doesn't indicate the shape of the returned weekend/price list or whether taxes are included, though the partial-answer sentence hints at structure.

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 baseline is 3. The description restates the free-vs-Pro gating that individual parameter descriptions already state, and adds no format or interaction detail beyond the schema (e.g., how out_from interacts with live-searched weekends is only in the schema).

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?

States a specific verb-like action and resource: 'Every weekend of the next 12 months for one origin-destination pair, with the cheapest round-trip price per weekend.' An agent knows exactly what it retrieves. However, it never distinguishes itself from the sibling 'cheapest_weekends', which sounds nearly identical in scope, leaving real ambiguity about which to pick.

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?

Gives clear operating context: free tier covers fri-sun/economy/any stops/any passenger mix, Pro session cookie required for other combos, cabins and time windows. It also tells the agent to call again if the live search doesn't finish. It stops short of explicit when-to-use-versus-'cheapest_weekends' guidance or exclusions.

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