Skip to main content
Glama

Pandex

Search legislation and court decisions

search
Read-onlyIdempotent

Find passages of legislation and court decisions. Answers with the passages themselves (an article, a paragraph of a judgment), each with its document, date, id and url. A query that names a text ("art. 6:162 BW", "§ 823 BGB", "ECLI:NL:HR:2019:2006", "32016R0679 art 17") is answered with that text first. Write the query in the language of the documents; set jurisdiction when you know it.

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": "search"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoOnly laws, only court decisions, or only treaties.
langNoTwo-letter language to match and answer in (texts that exist in several languages). Default: the query's language.
modeNohybrid (default) matches words and meaning; text only words; meaning only meaning.
citesNoOnly passages that cite this document or article: an id, id#element, or a citation.
courtNoWords from the court's name, e.g. "Hoge Raad", "Bundesgerichtshof", "Grand Chamber".
limitNoPassages to return, 1–20. Default 5.
queryYesWords, a question, or a citation. Put a phrase in double quotes to require it literally.
sourceNoSource ids from list_sources, comma-separated.
withinNoOnly passages of this document: an id or a citation.
date_toNoLatest document date, YYYY-MM-DD.
doc_typeNoA document type as shown in results, e.g. regulation, directive, act, judgment, opinion.
date_fromNoEarliest document date, YYYY-MM-DD.
max_tokensNoSize of the answer in tokens, 200–8000. Default 1500.
jurisdictionNoOne or more of: eu, coe (European Court of Human Rights), nl, fr, de, at, ch, lu, gb. Comma-separated.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower, and the description still adds real context: exactly what the answer contains (passage plus document, date, id, url), the ordering rule that a named text is returned first, and language-matching behavior. It does not discuss the 200–8000 max_tokens trade-off or what happens when nothing matches, which keeps it short of 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.

Conciseness5/5

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

Four sentences, each carrying distinct information: purpose, return shape, citation-resolution behavior, and query-language/jurisdiction advice. The most decisive fact, that results are passages, is front-loaded, and there is no filler.

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?

For a 14-parameter tool with no output schema, the description must carry the return contract, and it does so concretely by enumerating the fields bundled with each passage. The remaining gap is the absence of routing guidance versus the four sibling retrieval tools, which matters given how many overlapping ways exist to fetch legal text.

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 100%, so the baseline is 3, and the description earns above that by illustrating the citation syntaxes the query parameter accepts ("art. 6:162 BW", "§ 823 BGB", "ECLI:NL:HR:2019:2006", "32016R0679 art 17") and by explaining that query language should match the document language. It adds no meaning for the other 13 parameters, which the schema already covers.

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 ("Find passages of legislation and court decisions") and immediately qualifies the return unit as passages rather than whole documents, which implicitly separates it from get_document and get_outline. It never names a sibling or explicitly states the boundary, so an agent must infer routing from the return-shape hint alone.

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?

It gives query-writing advice ("Write the query in the language of the documents; set jurisdiction when you know it") and a behavioral rule that citation-shaped queries are resolved to that text first. There is no explicit when-to-use/when-not guidance and no pointing to get_document, get_citations, or list_sources as alternatives, so usage is implied rather than directed.

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.

Resources