Skip to main content
Glama

Gangwaze Cruise Tools

Search cruises

searchCruises
Read-onlyIdempotent

Search upcoming cruise sailings by destination, region, dates, length (nights "lo:hi"), cruise line, ship, departure port, ports of call, cabin type, budget, family fit and more. Pass the full filter set; omitted fields are unfiltered. Returns the match count, cheapest fare, top lines, the 10 soonest-departing sailings (results are always soonest first; each has an id for compareSailings/getPriceHistory) and a link to the full results on gangwaze.com.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cabinNoCabin-type keys, lowercase, from exactly: "inside", "oceanview", "balcony", "suite". Multiple values are OR-ed. Do not use any other spelling or capitalization (e.g. not "Suite") — unrecognised values are rejected.
portsNoPorts of call, exact catalogue names. OR-ed together. The tool resolves each against the real catalogue and returns suggestions for any name it does not recognise.
priceNoINSIDE-CABIN TOTAL price for the whole cruise, per person, in whole US dollars, as a colon-delimited INCLUSIVE range "lo:hi", e.g. "100:900" for $100 to $900. Open-ended ranges are allowed: "500:" or ":1500". Use this for a total budget ("under $1,500"); for a budget stated per day / per night use `pricePerNight` instead. Always the inside-cabin price, never other cabin types. Do NOT pass a bare number or a hyphenated range. null means no constraint.
shipsNoShip names, exact catalogue values. OR-ed together. The tool resolves each against the real catalogue and returns suggestions for any name it does not recognise.
vibesNoItinerary character, from exactly: "relaxing", "adventure", "nature", "shopping". OR-ed together. Map only what the user says ("a relaxing beach week" -> ["relaxing"]; "scenery and wildlife" -> ["nature"]); never infer a vibe from a destination. Empty array means no constraint.
familyNoFamily-suitability of the SHIP as a colon-delimited INCLUSIVE range "lo:hi" over a 0-100 score. "Family", "with the kids", "teens", "multi-generational" -> "60:"; "adults only", "couples retreat", "no kids", "quiet ship" -> ":40". Never quote the score to the user. Do NOT pass a bare number or a hyphenated range. null means no constraint.
nightsNoCruise length as a colon-delimited INCLUSIVE range "lo:hi", e.g. "7:7" for exactly 7 nights, "5:9" for 5 to 9 nights. Open-ended ranges are allowed: "5:" (5+ nights) or ":9" (up to 9 nights). Do NOT pass a bare number like "7" and do NOT use a hyphen like "5-9" — both are invalid and the filter will be rejected. null means no constraint.
safetyNoSafety score as a colon-delimited INCLUSIVE range "lo:hi" over a 0-100 scale, e.g. "80:100" for safety score 80 and up. Open-ended ranges are allowed: "80:" or ":50". Do NOT pass a bare number or a hyphenated range. null means no constraint.
endDateNoLatest sail date, as "YYYY-MM-DD" (e.g. "2027-06-30"). null means no upper bound.
regionsNoSub-region names, exact catalogue values (e.g. "Eastern Caribbean", "Western Mediterranean"). OR-ed together. The tool resolves each against the real catalogue and returns suggestions for any name it does not recognise — it is not case-sensitive but must be a real region.
lineTypeNoCruise-line tier, from exactly: "mainstream", "premium", "luxury", "river". OR-ed together. Use for "luxury cruise", "something upscale", "the big mainstream lines". A NAMED line ("Seabourn") goes in `cruiselines`, never here — this field is for when no line is named. Empty array means no constraint.
shipSizeNoShip size as PASSENGER CAPACITY (number of guests), as a colon-delimited INCLUSIVE range "lo:hi". Map words to these bands: "small ship" / "intimate" / "boutique" / "not a floating city" -> ":1500"; "mid-size" -> "1500:3000"; "big ship" / "mega-ship" / "lots to do on board" -> "3000:". A stated number works too: "under 1,000 passengers" -> ":1000". The fleet runs 100 to 7,600 guests. Open-ended ranges are allowed. Do NOT pass a bare number or a hyphenated range. null means no constraint.
shipYearNoYear the ship was BUILT, as a colon-delimited INCLUSIVE range "lo:hi", e.g. "2015:" for ships built in 2015 or later — this is how to answer "a newer ship". The catalogue spans 1998-2024. Open-ended ranges are allowed: "2015:" or ":2005". Note this is the build year, NOT the sail year — for when the cruise departs use startDate/endDate. Do NOT pass a bare number or a hyphenated range. null means no constraint.
startDateNoEarliest sail date, as "YYYY-MM-DD" (e.g. "2027-03-01"). null means no lower bound.
tripShapeNoWhether the cruise returns to where it started. "round_trip" for sailings that end at their departure port — use this when someone does not want to book two flights. "one_way" for sailings that end somewhere else, which includes repositioning cruises. Exactly those two strings; null means no constraint. About one in five sailings is one-way.
cruiselinesNoCruise line names, exact catalogue values (e.g. "Carnival Cruise Line", not "Carnival"). OR-ed together. The tool resolves each against the real catalogue and returns suggestions for any name it does not recognise.
destinationNoA single top-level region name, exact catalogue value (e.g. "Caribbean", "Europe", "Alaska") — NOT a sub-region like "Mediterranean" or "Eastern Caribbean" (those go in `regions`). Must be a real catalogue value; the tool returns suggestions if it is not recognised. null means no constraint.
departureDaysNoWeekday the cruise departs, from exactly: "mon", "tue", "wed", "thu", "fri", "sat", "sun". OR-ed together. "Weekend getaway" / "leave on the weekend" -> ["fri","sat"], and set `nights` to ":4" unless the user gave a length. A named day ("sails on a Saturday") -> that day. A short cruise on its own never implies a weekend. Empty array means no constraint.
pricePerNightNoINSIDE-CABIN price PER NIGHT, per person, in whole US dollars, as a colon-delimited INCLUSIVE range "lo:hi" — e.g. ":100" for "under $100 a day", "80:120" for $80 to $120 a night. Use this whenever the user states a budget per day, per night or per person per day; use `price` for a total. Divide nothing yourself — pass the per-night figure the user said. Do NOT pass a bare number or a hyphenated range. null means no constraint.
departurePortsNoDeparture/embarkation port names, exact catalogue values. OR-ed together. The tool resolves each against the real catalogue and returns suggestions for any name it does not recognise.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so the description correctly does not repeat the safety profile. It adds genuinely useful behavior: the 'omitted fields are unfiltered' rule and the deterministic soonest-first ordering, plus the 10-sailing cap and the external gangwaze.com link. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with the purpose front-loaded, followed by the key behavioral rule and then the return contract. Zero filler; every clause earns its place. Appropriate for a 20-parameter tool whose heavy detail lives in the schema.

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?

With no output schema, the description correctly takes on the return contract, disclosing match count, cheapest fare, top lines, the 10 soonest sailings and the external link. Combined with 100% schema coverage of all 20 parameters, nothing an agent needs to invoke it correctly is 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 description coverage is 100% with extremely detailed per-parameter guidance (formats, mapping rules, OR-ed behavior), so the baseline is 3. The description adds only a high-level enumeration of filter dimensions and the nights 'lo:hi' format hint; it does not meaningfully extend what the schema already documents, but it does not need to.

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 specific verb and resource — search upcoming cruise sailings — and enumerates the filter dimensions (destination, region, dates, length, line, ship, port, etc.). It is clearly distinct from the sibling get*/compare* tools, which perform different operations; the return statement even names compareSailings/getPriceHistory as downstream consumers, reinforcing what this tool is not.

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?

Provides clear context that this is the entry-point search tool whose returned ids feed into compareSailings/getPriceHistory, giving an agent an implicit call sequence. It does not, however, explicitly state when not to use it or name an alternative for a different need, so it stops short of full exclusion 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