Skip to main content
Glama

What's on in Hong Kong

get_events
Read-only

Big events in Hong Kong (concerts at the major venues, sports, festivals, arts), the same list as getaroundhongkong.com/events: titles in five languages, dates, venue, coordinates, nearest MTR station, and this site's page for getting there. Filter by dates (events overlapping from–to, Hong Kong dates, YYYY-MM-DD; from today on by default) and featured (the biggest, most crowded ones).

Input Schema

NameRequiredDescriptionDefault
toNoLast day, YYYY-MM-DD (default: everything coming up)
fromNoFirst day, YYYY-MM-DD (default today)
featuredNoOnly the featured (biggest) events

Output Schema

NameRequiredDescriptionDefault
toYesLast day covered, or null for everything coming up
fromYesFirst day covered, YYYY-MM-DD (Hong Kong)
eventsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedOutput schema / properties / events / items / properties / ends
      Added value: +{
      +  "description": "Roughly when it ends each day, HH:MM, Hong Kong: from its running time, else about 2.5 hours after a concert starts; null if not known",
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / events / items / properties / image
      Added value: +{
      +  "anyOf": [
      +    {
      +      "additionalProperties": false,
      +      "properties": {
      +        "credit": {
      +          "description": "Whose picture it is: credit it when showing it",
      +          "type": "string"
      +        },
      +        "focus": {
      +          "description": "Where to centre a crop, CSS background-position",
      +          "type": "string"
      +        },
      +        "height": {
      +          "type": "number"
      +        },
      +        "source": {
      +          "description": "The page it's from: link to it when showing it",
      +          "type": "string"
      +        },
      +        "url": {
      +          "description": "The event's own picture (its organiser's artwork), on this site",
      +          "type": "string"
      +        },
      +        "width": {
      +          "type": "number"
      +        }
      +      },
      +      "required": [
      +        "url",
      +        "width",
      +        "height",
      +        "credit",
      +        "source"
      +      ],
      +      "type": "object"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "Featured events' pictures; null until one is found"
      +}
    • changedOutput schema / properties / events / items / required
      Previous value: -[
      -  "id",
      -  "kind",
      -  "title",
      -  "start",
      -  "end",
      -  "time",
      -  "venue",
      -  "lat",
      -  "lon",
      -  "station",
      -  "url",
      -  "link",
      -  "featured"
      -]New value: +[
      +  "id",
      +  "kind",
      +  "title",
      +  "start",
      +  "end",
      +  "time",
      +  "ends",
      +  "venue",
      +  "lat",
      +  "lon",
      +  "station",
      +  "url",
      +  "link",
      +  "featured",
      +  "image"
      +]
  2. Added

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare read-only, open-world access. The description adds real context beyond that: the data source, exactly what each result contains (five-language titles, coordinates, nearest MTR, page link), and default date scoping. This is useful behavioral framing, not repetition.

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?

A single dense sentence that front-loads what the tool returns and follows with filter semantics. It never wastes words, though the parenthetical lists make it slightly run-on for scanning.

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?

The output schema and annotations already cover return shape and safety, and the description fills in source, fields, and default filtering. It's complete for invocation; the only miss is not guiding the agent toward siblings.

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 3 is a baseline. The description goes further by clarifying that 'from' defaults to today and that filtering is by events overlapping the from–to range with Hong Kong dates — meaning the schema's 'First day'/'Last day' labels don't fully convey.

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 resource (big events in Hong Kong) with concrete categories (concerts at major venues, sports, festivals, arts) and ties it to a recognizable source (getaroundhongkong.com/events). It doesn't explicitly distinguish itself from siblings like search_place, but the domain is clearly distinct.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It implies when to use it (to find events) and explains the two filters (dates, featured) with defaults ('from today on by default'). However, it never names alternatives or says when another tool is the better choice.

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