Skip to main content
Glama

Port day guide (time ashore, nearby destinations, places)

port_day_guide
Read-onlyIdempotent

Plan one time-boxed day in an unfamiliar port city — typically a cruise port day, or any stop with a fixed arrival and departure time. Given the port and the ship's local arrival and departure times, returns: the usable time ashore (after disembarking, keeping a safe return margin before all-aboard), each nearby destination with its round-trip travel time, the time left there and a good/tight/skip verdict, up to 8 recommended places, transport routes from the pier with durations and fares, the cruise terminals, and verified facts (closures, entry rules, prices) with source links. Use it for questions like "We are in Livorno 07:00–19:00 — can we see Florence?" or "What can we do in Keelung from 13:00 to 18:00?". Covers 200+ cruise ports from the Cruise Planner(크루즈 플래너) port guide; for a port that does not match it returns the time window and up to 5 similar guide ports. Fields listed in text_fields are in Korean (text_language "ko"). No ratings, reviews or opening hours.

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": {
      "port": "<port>",
      "arrival_time": "<arrival_time>",
      "departure_time": "<departure_time>"
    },
    "name": "port_day_guide"
  }
}

Input Schema

NameRequiredDescriptionDefault
portYesPort name in English or Korean (e.g. "Livorno", "Keelung", "리보르노") or its UN/LOCODE (e.g. "ITLIV"). Matched exactly (case, spacing and punctuation ignored), not by similarity. If it is not found, the response suggests up to 5 similar guide ports (port_candidates); their port_key is accepted here.
tenderNoTrue if passengers go ashore by tender boat at this call. Optional; otherwise taken from the port guide when known.
arrival_timeYesShip arrival time at the port, local time, 24h HH:mm (e.g. "07:00"). Required.
user_languageNoThe traveler's language as a BCP 47 tag (e.g. "en", "ja", "ko", "zh-TW"). Korean (ko or ko-*) or a missing value opens Korean UI; English (en or en-*) and any other language or invalid tag opens English UI. Valid tags are used for anonymous usage statistics and preserved as a language hint in a chosen-cruise start link. It does not translate narrative answers or saved plan content. The returned ui_language reports the language actually used.
departure_timeYesShip departure time, local time, 24h HH:mm (e.g. "19:00"). Required. If earlier than arrival_time it is read as the next day (overnight call).
all_aboard_timeNoOfficial all-aboard time if the cruise line published one (HH:mm). Optional; otherwise 60 minutes before departure is assumed as a planning rule.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare read-only, idempotent, non-destructive, closed-world; the description goes well beyond them by disclosing coverage (200+ ports), the fallback behavior on no match, the Korean text-field caveat, and deliberate exclusions (no ratings, reviews or opening hours). An agent knows both what it gets and what it must not expect.

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 purpose and return payload before examples and caveats; nearly every clause carries information. It is dense rather than padded, though the long single paragraph and dual example questions make it slightly heavier than necessary.

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?

There is no output schema, so the description must describe returns — and it does thoroughly, field by field, including the verdict scale and the unmatched-port response. Combined with a fully documented schema, an agent has everything needed to call and interpret this tool.

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 matching rules, the overnight interpretation, the 60-minute all-aboard default and language handling are all already documented in the schema. The description reinforces the time-window framing with examples but adds no parameter meaning the schema lacks, so the baseline of 3 applies.

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 — 'plan one time-boxed day' in a port city with fixed arrival/departure — and enumerates exactly what comes back (usable time ashore, destinations with verdicts, places, transport, terminals, sourced facts). This is clearly distinct from the sibling tools (plan status, connections, start plan).

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 worked example questions ('We are in Livorno 07:00–19:00 — can we see Florence?') and scopes the tool to any stop with a fixed arrival and departure time, so applicability is easy to infer. It also documents the miss path (up to 5 similar guide ports). It does not explicitly contrast itself with the sibling tools, which keeps it short of a 5.

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