Skip to main content
Glama

doctrine_research

Read-onlyIdempotent

Find legislation hits and ranked case leads for a Hong Kong criminal-law doctrine or issue, then verify citations before relying on them.

Instructions

Return legislation hits and ranked case leads for a doctrine or issue.

live_cases follows HK_LAW_LOCAL_ONLY; the public release can opt into local-only. This is a discovery pack, not a legal answer. Fetch and read the judgments you intend to cite.

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": {
      "query": "<query>"
    },
    "name": "doctrine_research"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNoen
queryYes
case_limitNo
live_casesNo
legislation_limitNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.3.0
    • addedInput schema / properties / live_cases / anyOf
      Added value: +[
      +  {
      +    "type": "boolean"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / properties / live_cases / default
      Previous value: -falseNew value: +null
    • removedInput schema / properties / live_cases / type
      Removed value: -"boolean"
  2. First observedv0.2.0

TDQS

B3.4/5.0
Behavior4/5

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

The annotations already cover safety (readOnly, idempotent, non-destructive, openWorld), so the description's added value is the governance note: `live_cases` follows `HK_LAW_LOCAL_ONLY` and the public release can opt into local-only, plus the warning that results are leads, not citable answers. It does not disclose how leads are ranked, how many sources are consulted, or any latency/scope limits, so it is not exhaustive.

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 purpose is front-loaded in the first sentence and the remaining sentences are caveats rather than filler. The backticked-line-break formatting of the `live_cases` note is slightly awkward to parse, but there is no redundant material.

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 5 parameters, 0% schema coverage and no output schema, the description should say more about what a 'hit' or 'lead' contains and how limits interact. It communicates the tool's role and the local-only constraint well, but leaves the return shape and most parameter behavior to inference.

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 5 parameters, so the description must carry the burden. It only explains `live_cases` (tied to an environment flag), leaving `query`, `lang`, `case_limit` and `legislation_limit` with nothing beyond bare titles and defaults. The one param it does explain is genuinely non-obvious, which prevents a 1.

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 first sentence gives a concrete verb ('Return') and two concrete resources ('legislation hits and ranked case leads') scoped to 'a doctrine or issue', which is more than a restatement of the name. It implicitly reads as a combined discovery tool rather than a pure case or statute search, but it never names `search_cases` or `search_legislation` to make the boundary explicit.

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?

'This is a discovery pack, not a legal answer. Fetch and read the judgments you intend to cite' clearly frames it as a first-pass orientation step followed by `get_case`-style retrieval. That is real when-to-use guidance, but it stops short of stating when to prefer this over the sibling search tools, or any exclusion conditions.

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