Skip to main content
Glama

get_case_paragraphs

Read-onlyIdempotent

Retrieve specific paragraphs from Hong Kong criminal case judgments by citation for targeted legal research, with local-only defaults and optional live retrieval.

Instructions

Return specific paragraphs, local by default.

allow_live follows HK_LAW_LOCAL_ONLY just like :func:get_case.

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>",
      "paragraphs": "<paragraphs>"
    },
    "name": "get_case_paragraphs"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNoen
citationYes
allow_liveNo
paragraphsYes

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

C2.6/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds real value by disclosing the local-by-default behavior and tying `allow_live` to the `HK_LAW_LOCAL_ONLY` environment variable, but says nothing about what happens when a requested paragraph is absent or what the response looks like.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short and front-loaded, so no padding is present. But the second sentence leaks Sphinx markup (`:func:`get_case``) and assumes the reader knows what `HK_LAW_LOCAL_ONLY` does, so the brevity comes at the cost of self-containment.

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

Completeness2/5

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

With no output schema and zero parameter documentation, the description should carry more weight. It leaves the paragraph identifier format, the meaning of `lang`, and the failure behavior for missing paragraphs unspecified — significant gaps for a four-parameter retrieval tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across four parameters, so the description must compensate and largely does not. It illuminates only `allow_live` (and only by reference to an environment variable); `citation`, `paragraphs` (array of strings — are these numbers, labels, or ranges?) and `lang` are entirely undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Return specific paragraphs" names a verb and a resource, and the tool name plus the required `citation` parameter make it reasonably clear this is a subset-of-a-case retrieval. However, the description never states that the paragraphs come from a case identified by citation, nor does it distinguish the scope from the sibling `get_case`, which returns the whole document.

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

Usage Guidelines2/5

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

The only guidance is "local by default" and the `allow_live` / `HK_LAW_LOCAL_ONLY` note. There is no statement of when to prefer this over `get_case`, or when a caller should set `allow_live`, leaving the choice to inference.

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