Skip to main content
Glama

Honee – cruise · honeefy

Find bookable cruises

find_cruises
Read-onlyIdempotent

Searches the live, bookable sea and river cruise offers of cruise · honeefy (booked through honeepot GmbH) for a destination, a travel period and a travel party. Prices and availability are read from the provider's booking system at the time of the call and change several times a day. It fits questions about this provider's cruise offers, prices, dates and availability, and when the user wants to see, compare or book its cruises. Requires adults, period (or from_date/to_date) and destination — if any is missing, unusable or not a region this provider can search, the result lists a question for it and no search runs; ask the user, then call again with the same handle. For river cruises pass cruise_type='river' (a river name such as 'Danube' is recognised too). Sea cruises are shown WITHOUT a flight package by default; pass flight='with' to get the flight packages instead. Returns a summary plus up to 10 offers with cruise_id, ship, cruise line, dates, nights, price with currency (per person; for families the cabin total for the whole party where the provider computes it) and the booking link. Where the provider supports it, availability is checked LIVE for the top offers and each says whether it is confirmed; sold-out ones are removed. The list is a SAMPLE of the provider's matches: the result says how many exist and which cruise lines have sailings -- never conclude that a line is not offered because it is not listed; pass cruise_line to look for it. It does NOT show anything to the user, book or hold cabins, know availability beyond what it returns, or search by price alone. Each offer carries its price per cabin category; pass cabin when the user names a cabin type. When you name or recommend offers from the result, call show_offers ONCE afterward with their cruise_id values (3-5; exactly ONE when the user asks which single cruise you recommend), so the user sees them as cards. Never invent offers that are not in the result.

Input Schema

NameRequiredDescriptionDefault
cabinNoCabin category the user asked for ('outer' = outside or ocean view). Only if the user names one; the result then quotes the price of that category.
limitNoHow many offers to return as data (3-10, default 10). The result also carries `total` and `links.all` (every match on the provider's search page).
portsNoPorts, islands or countries that must ALL be on the route (start, a stop or the end), e.g. ['Barbados', 'St. Lucia'] or the port cities ['Bridgetown', 'Castries'] -- an island/country entry matches any of its ports on the route. Names are matched in English; a translated name may find nothing, try the English or the specific port city instead.
adultsNoNumber of adults travelling.
flightNo'without' (default): cruise only. 'with': the provider's flight packages.
handleNoConsultation handle returned by a previous call (structuredContent.handle). Pass it on every call so wishes are remembered; omit it on the very first call.
periodNoTravel period as free text, e.g. 'summer 2027', 'October 2027', '2027-06-01 to 2027-06-30'.
to_dateNoLatest departure, ISO date. Alternative to period.
languageNoLanguage of the answer. Defaults to the provider's language.
from_dateNoEarliest departure, ISO date. Alternative to period.
nights_maxNoMaximum nights. Only if the user names a trip length; below 4 nights asks for short cruises first.
nights_minNoMinimum nights. Only if the user names a trip length.
cruise_lineNoCruise line(s) by name, e.g. 'MSC' or 'MSC, AIDA' (comma-separated). The search is filtered AT THE PROVIDER, so use it to look for a line the default list does not show.
cruise_typeNo'ocean': sea cruises. 'river': river cruises (Danube, Rhine, Moselle, Nile, ...). Omit it to derive it from the destination.
destinationNoRegion, country, sea or river in any language, e.g. 'Mediterranean', 'Norwegian fjords', 'Caribbean', 'Danube'. For a river cruise on any river pass 'river cruise'.
children_agesNoAge of each child at travel time. A child without an age is not searched for.
departure_portNoA single port that must be on the route (start, stop or end), e.g. 'Barcelona'. For several required ports use `ports` instead.
departure_airportNoDeparture airport(s) for flight packages: a city or IATA code, e.g. 'Bremen' or 'BRE'; several separated by commas or 'or', e.g. 'Bremen, Hannover'. Only used together with flight='with' (set it when the user wants to fly from a named airport). Cabin prices then include the flight from that airport. An airport the provider market does not know is asked back, never guessed.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / departure_airport
      Added value: +{
      +  "description": "Departure airport(s) for flight packages: a city or IATA code, e.g. 'Bremen' or 'BRE'; several separated by commas or 'or', e.g. 'Bremen, Hannover'. Only used together with flight='with' (set it when the user wants to fly from a named airport). Cabin prices then include the flight from that airport. An airport the provider market does not know is asked back, never guessed.",
      +  "type": "string"
      +}
  2. Changed1 schema field changed
    • addedInput schema / properties / cabin
      Added value: +{
      +  "description": "Cabin category the user asked for ('outer' = outside or ocean view). Only if the user names one; the result then quotes the price of that category.",
      +  "enum": [
      +    "inside",
      +    "outer",
      +    "balcony",
      +    "suite"
      +  ],
      +  "type": "string"
      +}
  3. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/openWorld, and the description adds genuinely non-obvious traits: prices are read live and change several times a day, results are a capped sample with a total count, sold-out offers are removed, top offers get a live availability check, and cruise_line filters at the provider. This is exactly the context annotations cannot convey.

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?

It is long, but front-loaded with purpose first, then the failure protocol, then behavioral caveats, then the show_offers handoff. A few clauses are redundant (the 'does NOT' list partially repeats earlier statements), which keeps it from a 5.

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 18 parameters, no output schema and open-world search semantics, the description covers required inputs, the missing-input loop, result shape (summary plus up to 10 offers with cruise_id, ship, dates, price, booking link), sampling limits, and the follow-up call. Nothing an agent needs in order to call it correctly is missing.

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 real meaning beyond it: river names may be passed as destination, river cruises should use cruise_type='river', flight='with' switches to flight packages, cabin prices are per person, and cruise_line is the escape hatch when a line is not in the sample. It does not explain handle/limit/nights_* beyond the schema, keeping it just short of 5.

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 ('searches the live, bookable sea and river cruise offers') plus the provider scope, and explicitly names the sibling it feeds into (show_offers). An agent can tell it apart from cruise_line_profile, ship_profile and show_offers without opening any schema.

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 when-to-use ('questions about this provider's cruise offers, prices, dates and availability'), when-not-to-use ('does NOT show anything to the user, book or hold cabins, or search by price alone'), the retry protocol when required inputs are missing (ask the user, call again with the same handle), and the downstream rule to call show_offers once with 3-5 ids.

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