Skip to main content
Glama

Hk New Companies

hk_new_companies
Read-onlyIdempotent

Companies newly incorporated (Hong Kong local) or newly registered/re-domiciled (non-Hong Kong) on the Companies Registry since a given date, the official weekly open-data feed via data.gov.hk (新註冊/新成立公司, since 2024-12-30). Returns each company's BR number, English/Chinese name, type, and incorporation-or-registration date, most recent first. The feed has roughly a 1-week publication lag, so a since newer than the latest published week returns zero rows with a data_lag_note explaining it, that is lag, not "no new companies". Use for "new Hong Kong companies this week", "companies incorporated in HK since ".

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "since": "2026-08-24"
    },
    "name": "hk_new_companies"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeNoRestrict to Hong Kong local companies ("local") or non-Hong Kong companies ("non_hk"). Omit for both.
limitNoMax companies to return, 1-200 (default 50).
sinceNoOnly include companies incorporated/registered on/after this date (YYYY-MM-DD). Default: 7 days before the latest published week.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations only declare it as a safe read; the description adds real operational context beyond them: the ~1-week publication lag, the fact that a too-recent `since` yields zero rows plus a `data_lag_note`, and that zero results mean lag rather than no new companies. It also states ordering (most recent first). It doesn't cover pagination limits beyond what the schema says, keeping it below a 5.

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-loads the core definition, then the return fields, then the lag caveat and use cases, with no filler. The opening sentence is long and clause-heavy, which slightly slows scanning, but every sentence carries information.

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 compensates by enumerating the returned fields (BR number, names, type, date) and the ordering. The lag/zero-row behavior is explained, which is the main failure mode. Minor gaps remain around result volume and how to page through the feed, but the definition is essentially complete for a 3-param read 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 all three parameters (type, limit, since) are already documented, including the enum values and the `since` default. The description reinforces the `since` semantics and its interaction with the lag, but adds no per-parameter detail the schema lacks; baseline 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+resource (companies newly incorporated / newly registered or re-domiciled) plus the source (Companies Registry weekly open-data feed via data.gov.hk) and the fields returned. An agent can distinguish this 'new incorporations feed' from sibling lookups like hk_company or hk_company_search without opening a schema.

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 triggering phrasings ('new Hong Kong companies this week', 'companies incorporated in HK since <date>'), which is clear context for when to reach for it. It does not explicitly name an alternative sibling or state when-not to use it (e.g., for existing-company lookups), so it stops short of full routing 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.