Skip to main content
Glama

get_case

Read-onlyIdempotent

Read a Hong Kong judgment by citation, with optional language, paragraph ranges, and character limits; retrieves locally by default and allows live lookup when enabled.

Instructions

Read a Hong Kong judgment, local by default.

Args: citation: e.g. "[2021] HKCFA 1". lang: "en" or "zh-Hant". paragraphs: Optional paragraph numbers/ranges, e.g. ["12", "15-17"]. max_chars: Truncate the returned full text to this many characters. allow_live: Defaults to HK_LAW_LOCAL_ONLY=0 (live when local-only is off); otherwise a missing case is a coverage gap, not an error to paper over.

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": {
      "citation": "<citation>"
    },
    "name": "get_case"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNoen
citationYes
max_charsNo
allow_liveNo
paragraphsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.3.0
    • addedInput schema / properties / allow_live
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "boolean"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Allow Live"
      +}
  2. First observedv0.2.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, so the safety profile is covered. The description adds non-obvious behavior: resolution is local-first with live lookup governed by HK_LAW_LOCAL_ONLY, and an unresolved citation is treated as a coverage gap rather than an error — exactly the kind of thing an agent needs before deciding to retry or escalate.

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?

The one-line purpose is front-loaded, then a compact Args block maps sentence-for-sentence to parameters with no filler. The closing clause ("not an error to paper over") is slightly editorial but still conveys actionable behavior rather than noise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and no annotations about return shape, the description only implies the return value via "Truncate the returned full text." It never says whether metadata (court, date, parties) accompanies the text, nor what an empty or partial result looks like — a meaningful omission for a primary document-retrieval tool.

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 description coverage is 0%, so the description carries the full burden and largely meets it: it gives a citation format example, enumerates the lang values ("en" or "zh-Hant"), shows paragraph range syntax ("15-17"), and explains max_chars as truncation of full text plus the allow_live default resolution. It does not state the default max_chars value or the effect of requesting paragraphs alongside truncation, leaving minor gaps.

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?

The description opens with a specific verb and resource: "Read a Hong Kong judgment," and adds a scope qualifier ("local by default"). It is clear enough to distinguish from search_cases or verify_citation, though it does not explicitly contrast with the close sibling get_case_paragraphs, which also retrieves paragraph-level content.

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?

Usage is implied by the required citation parameter rather than stated: an agent can infer this is the fetch-by-citation tool. The allow_live note gives real guidance about when live fetching applies and that a miss is a coverage gap, but there is no explicit routing advice (e.g., when to prefer get_case_paragraphs for paragraph extraction instead of using the paragraphs arg here).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.