Skip to main content
Glama

Build a full trip plan for a chosen cruise

plan_cruise_trip

Build a complete Cruise Planner(크루즈 플래너) trip plan around a cruise the traveler has already chosen: flights, hotels before and after the cruise, and a plan for each port day. First call: ship_name and departure_date (plus nights or embark_port when several sailings share the ship and date). The response gives plan_ref and missing_fields. Answers for missing_fields are accepted in the same call or in a later call with plan_ref. When nothing is missing, planning starts on our side and can take several minutes. A call with plan_ref also reports progress. When status is "ready", share_url opens the finished trip guide (no sign-in needed) and pdf_url downloads it. The plan language and the default home airport are fixed by the first call (user_language). Responses carry status, plan_ref, open questions, stage progress and, when ready, links and plan_itinerary (the day-by-day plan, without prices). Does not search, compare, price or book cruises.

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": "plan_cruise_trip"
  }
}

Input Schema

NameRequiredDescriptionDefault
paceNoPreferred pace in port as a short phrase (e.g. "relaxed", "packed"). Optional; accepted together with port_interests or after port_interests was recorded.
cabinsNoNumber of cabins, asked when three or more paying travelers (adults and children) share the trip. Accepted together with travelers or after travelers was recorded.
nightsNoNumber of nights. Optional; narrows the match when several sailings share the ship and date.
walkingNoHow much walking suits the group: normal or easy. Optional; accepted like pace.
plan_refNoReference from an earlier plan_cruise_trip response. Use it for every call after the first. Each response returns a fresh plan_ref, valid for 7 days from that response.
companionNoWho is traveling: couple, solo, family (with children), parents (with the traveler's parents), friends.
ship_nameNoExact English ship name (e.g. "MSC World Europa"). Required on the first call (without plan_ref). Matched exactly, not by similarity; an unknown name returns the covered ships (catalog_ships).
travelersNoNumber of travelers. children are ages 2-17, infants are under 2.
embark_portNoEmbarkation port name or UN/LOCODE. Optional; narrows the match like nights.
home_airportNoCity or airport the traveler flies from (name or IATA code). Asked for English-language plans; Korean-language plans default to Incheon (ICN).
user_languageNoThe traveler's language as a BCP 47 tag (e.g. "en", "ja", "ko"). Required on the first call (without plan_ref). The first call fixes the plan language: Korean (ko or ko-*) makes a Korean plan with Incheon (ICN) as the default home airport; English (en or en-*) and any other language or invalid tag makes an English plan, and home_airport is then asked. On later calls it sets only the language of the returned links (ui_language).
departure_dateNoEmbarkation date, YYYY-MM-DD (local date at the embarkation port). Required on the first call.
port_interestsNoWhat the traveler likes to do in port, as short phrases (e.g. "old town walks", "local food", "beaches"). Up to 8.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior5/5

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

Annotations only say readOnlyHint=false and idempotentHint=false; the description supplies the real behavioral picture: planning runs asynchronously and can take several minutes, progress is pollable via plan_ref, status "ready" yields a share_url requiring no sign-in and a pdf_url, and each response returns a fresh plan_ref valid for 7 days. It also discloses a sticky side effect the annotations cannot express — the first call permanently fixes plan language and default home airport.

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 the purpose, then ordered by call lifecycle (first call → missing fields → polling → ready), which matches how an agent will use it. It is dense but long, and the language/home-airport rule is restated in both the prose and the user_language schema, so a little redundancy could be trimmed.

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-output-schema, asynchronous tool, the description does the heavy lifting: it enumerates the response envelope (status, plan_ref, open questions, stage progress, links, plan_itinerary without prices) and explains the state machine. Remaining gaps are minor, such as error behavior beyond the unknown-ship case, which the schema covers.

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

Parameters4/5

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 conditional logic the schema does not state as directly: which parameters are mandatory on the first call versus later, that nights/embark_port only narrow a ship-and-date match, and that user_language on later calls governs only the language of returned links. That is genuine added meaning beyond the already-verbose field descriptions.

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 and resource: builds a full trip plan (flights, pre/post-cruise hotels, per-port-day plans) around an already-chosen cruise, and explicitly scopes out search/compare/price/book. It is clear what the tool does, but it never names its closest siblings (start_cruise_plan, get_plan_status) to disambiguate, even though it partially duplicates the status-reporting behavior of get_plan_status.

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 concrete sequencing guidance: first call needs ship_name and departure_date (plus nights/embark_port when several sailings share ship and date), later calls use plan_ref, and missing_fields answers may be supplied in the same or a later call. What it lacks is explicit routing against the sibling tools, so the agent must infer when to pick this over start_cruise_plan or get_plan_status.

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