Skip to main content
Glama

search_caselaw

Search court decisions and case law in a chosen jurisdiction by keyword, date, court, or other filters, then get identifiers to fetch full decisions.

Instructions

Search court decisions (case law / precedent) in one jurisdiction.

Most sources search the full text; some search only titles, parties or metadata, and a few ignore the words (the result header and Note say so; see list_jurisdictions Notes). A count of 0 may then mean "not searchable this way", not "no such decision".

Args: jurisdiction: code from list_jurisdictions, e.g. "nl", "gb" (alias "uk"). query: search words in the language of the source (Dutch for nl, English for gb). May be empty ("") for sources that can list by filters alone (date, court, number). Date, court, type, year and similar narrowing belong INSIDE filters; any other top-level argument is rejected. limit: results per page (default 10). page: 1-based page number. filters: optional jurisdiction-specific filters as a dict, e.g. {"sort": "uitspraak", "period": "dit_jaar"} for nl or {"court": "uksc,ewca/civ", "order": "-date"} for gb. The valid names differ per jurisdiction; see list_jurisdictions.

Returns a markdown list; each hit has the identifier to pass to get_decision. Snippets are not enough to cite: fetch the full decision.

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": {
      "jurisdiction": "<jurisdiction>"
    },
    "name": "search_caselaw"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNo
limitNo
queryNo
filtersNo
jurisdictionYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full burden. It does disclose important behavioral quirks (some sources index only titles/parties/metadata, a few ignore the query entirely, and the header/Note signals which) plus the return shape (markdown list with identifiers). It says nothing about pagination limits, permissions, or rate limits, so the behavioral picture is good but not complete.

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 opening sentence is front-loaded with purpose, then a caveat paragraph, then an Args block that is easy to scan. Length is justified by five undocumented parameters, though the caveat paragraph about non-searchable sources is slightly dense and could be tightened.

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?

Covers what an agent needs to call it correctly: jurisdiction sourcing, language of the query, filter placement, paging, and the follow-up fetch step. An output schema exists so return-value detail is not required, and the description still notes the markdown-list shape.

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 0%, yet every parameter is explained: jurisdiction as a code from list_jurisdictions with an alias example, query as source-language words that may be empty for filter-only listing, limit as results per page, page as 1-based, and filters as a jurisdiction-specific dict with two worked examples. It stops short of naming the valid filter keys per jurisdiction, deferring to list_jurisdictions, which keeps it a 4 rather than a 5.

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 and resource ("Search court decisions (case law / precedent)") and scopes it to "one jurisdiction", which cleanly separates it from search_legislation and the get_* siblings. The mention that each hit carries the identifier for get_decision also pins down its position in a workflow.

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

Usage Guidelines5/5

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

Explicitly routes the agent to list_jurisdictions for jurisdiction codes and valid filter names, and warns that filters like date/court/year must go inside `filters` while any other top-level argument is rejected. It also covers a non-obvious failure mode: a count of 0 may mean "not searchable this way", and snippets must be followed up with get_decision before citing.

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