Skip to main content
Glama

Armá tu viaje con Wizzo

trip_chat

Talk to Wizzo, WizTrip's travel agent from wiz-trip.com/arma-tu-viaje, to build a trip: destinations, dates, travellers, flights and hotels, single or multi-city. Pass the traveller's request as message (in Spanish if they speak Spanish; Wizzo answers in Spanish). The first call starts a trip and returns its trip_id: pass it on every following call. Wizzo searches real flights and hotels and may show options to choose (use trip_choose). Relay what Wizzo says faithfully; prices are WizTrip selling prices in USD. When the trip is ready the card shows «Reservar ahora», which opens the wiz-trip.com checkout where the person pays. The card shows Wizzo's words, the options and the booking buttons. Today is 2026-11-19. Each call returns within seconds; while Wizzo is still working the answer gives a turn_id: call trip_chat again right away with the same trip_id and that turn_id, without message, until Wizzo answers. Never send the same message twice.

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": "trip_chat"
  }
}

Input Schema

NameRequiredDescriptionDefault
messageNoThe traveller's message to Wizzo.
trip_idNoThe trip id returned by a previous trip_chat call. Omit it to start a new trip.
turn_idNoOnly to keep waiting on a turn that was still running: the turn_id it returned.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations only mark it as non-read-only, non-destructive and non-idempotent; the description goes much further, disclosing the trip_id/turn_id lifecycle, that calls return within seconds but may still be running, that prices are WizTrip selling prices in USD, that the checkout happens on wiz-trip.com, and what the returned card displays.

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-loads purpose and then the state machine, with almost no filler. A few clauses are near-duplicative (the Spanish-language note appears twice) and the polling instruction is dense, but nothing is expendable for correct invocation.

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?

No output schema exists, yet the description explains what comes back (trip_id, turn_id, card contents, booking buttons) and where payment happens, so an agent can drive the full multi-turn flow. Given three optional parameters and no output schema, nothing essential is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

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 real meaning: `message` should carry the traveller's request verbatim in the traveller's language, `trip_id` must be echoed on every subsequent call, and `turn_id` is only for continuing an unfinished turn and must be sent without `message`.

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?

States a concrete verb and resource — talk to Wizzo, WizTrip's travel agent, to build a trip (destinations, dates, travellers, flights, hotels, single or multi-city) — and names the entry point URL. It is clearly distinguishable from siblings like search_flights or trip_choose, which it explicitly defers to for option selection.

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?

Gives explicit sequencing rules: first call starts a trip, every later call must carry the returned trip_id, use trip_choose when options are shown, and never resend the same message. It also spells out the exact wait protocol (call again with trip_id + turn_id and no message until Wizzo answers).

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