Skip to main content
Glama

Lex — Temporal Luxembourg and EU Law

search

Filtered legal search. keyword is deterministic FTS5/BM25; hybrid adds the pinned local encoder and fixed RRF when verified vectors are mounted. No generative model participates. The response query_plan separates resolved work constraints, article and role intent, and residual provision terms. Returns hits WITHOUT body text; full state via as_of.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
as_ofNoISO date required when time_scope=as_of
fuzzyNoauto or off; visible fallback only
limitNodefault 10; minimum 1, maximum 50
queryYessearch terms
worksNooptional comma-separated work ids: restrict search to these works
domainNolegacy domain id filter; current v4 indexes leave it empty; use publisher_metadata_identifier for official classifications
act_formNooptional legal act form
languageNooptional language code
hierarchyNooptional normalized legal hierarchy
publisherNooptional publisher id
time_scopeNoall_versions or as_of
jurisdictionNooptional jurisdiction code from index metadata, e.g. LU or EU
source_classNooptional source document class
document_typeNobackward-compatible document type filter
binding_statusNooptional binding status
retrieval_modeNokeyword or hybrid; default keyword until activation
publisher_metadata_identifierNooptional exact official publisher-metadata URI returned by a search hit

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed4 schema fields changed
    • addedInput schema / allOf
      Added value: +[
      +  {
      +    "if": {
      +      "properties": {
      +        "time_scope": {
      +          "const": "as_of"
      +        }
      +      },
      +      "required": [
      +        "time_scope"
      +      ]
      +    },
      +    "then": {
      +      "required": [
      +        "as_of"
      +      ]
      +    }
      +  }
      +]
    • changedInput schema / properties / as_of / pattern
      Previous value: -"^[0-9]{4}-[0-9]{2}-[0-9]{2}$"New value: +"^\\d{4}-(0[1-9]|1[0-2])-(0[1-9]|[12][0-9]|3[01])$"
    • changedInput schema / properties / domain / description
      Previous value: -"optional reviewed legal domain id"New value: +"legacy domain id filter; current v4 indexes leave it empty; use publisher_metadata_identifier for official classifications"
    • addedInput schema / properties / publisher_metadata_identifier
      Added value: +{
      +  "description": "optional exact official publisher-metadata URI returned by a search hit",
      +  "maxLength": 2048,
      +  "minLength": 1,
      +  "pattern": "^https?://",
      +  "type": "string"
      +}
  2. Changed35 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / act_form / maxLength
      Added value: +1000
    • addedInput schema / properties / act_form / minLength
      Added value: +1
    • addedInput schema / properties / as_of / maxLength
      Added value: +10
    • addedInput schema / properties / as_of / minLength
      Added value: +1
    • addedInput schema / properties / as_of / pattern
      Added value: +"^[0-9]{4}-[0-9]{2}-[0-9]{2}$"
    • addedInput schema / properties / binding_status / maxLength
      Added value: +1000
    • addedInput schema / properties / binding_status / minLength
      Added value: +1
    • addedInput schema / properties / document_type / maxLength
      Added value: +1000
    • addedInput schema / properties / document_type / minLength
      Added value: +1
    • addedInput schema / properties / domain / maxLength
      Added value: +1000
    • addedInput schema / properties / domain / minLength
      Added value: +1
    • addedInput schema / properties / fuzzy / enum
      Added value: +[
      +  "auto",
      +  "off"
      +]
    • addedInput schema / properties / fuzzy / maxLength
      Added value: +64
    • addedInput schema / properties / fuzzy / minLength
      Added value: +1
    • addedInput schema / properties / hierarchy / maxLength
      Added value: +1000
    • addedInput schema / properties / hierarchy / minLength
      Added value: +1
    • addedInput schema / properties / jurisdiction / maxLength
      Added value: +64
    • addedInput schema / properties / jurisdiction / minLength
      Added value: +1
    • addedInput schema / properties / language / maxLength
      Added value: +16
    • addedInput schema / properties / language / minLength
      Added value: +1
    • addedInput schema / properties / publisher / maxLength
      Added value: +64
    • addedInput schema / properties / publisher / minLength
      Added value: +1
    • addedInput schema / properties / query / maxLength
      Added value: +1000
    • addedInput schema / properties / query / minLength
      Added value: +1
    • addedInput schema / properties / retrieval_mode / enum
      Added value: +[
      +  "keyword",
      +  "hybrid"
      +]
    • addedInput schema / properties / retrieval_mode / maxLength
      Added value: +64
    • addedInput schema / properties / retrieval_mode / minLength
      Added value: +1
    • addedInput schema / properties / source_class / maxLength
      Added value: +1000
    • addedInput schema / properties / source_class / minLength
      Added value: +1
    • addedInput schema / properties / time_scope / enum
      Added value: +[
      +  "all_versions",
      +  "as_of"
      +]
    • addedInput schema / properties / time_scope / maxLength
      Added value: +64
    • addedInput schema / properties / time_scope / minLength
      Added value: +1
    • addedInput schema / properties / works / maxLength
      Added value: +1000
    • addedInput schema / properties / works / minLength
      Added value: +1
  3. Changed3 schema fields changed
    • changedInput schema / properties / limit / description
      Previous value: -"default 10"New value: +"default 10; minimum 1, maximum 50"
    • addedInput schema / properties / limit / maximum
      Added value: +50
    • addedInput schema / properties / limit / minimum
      Added value: +1
  4. Changed1 schema field changed
    • changedInput schema / properties / domain / description
      Previous value: -"optional reviewed EU domain id"New value: +"optional reviewed legal domain id"
  5. Changed1 schema field changed
    • changedInput schema / properties / jurisdiction / description
      Previous value: -"optional lu or eu"New value: +"optional jurisdiction code from index metadata, e.g. LU or EU"
  6. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Without annotations, the description carries the full burden and does well: it discloses the deterministic FTS5/BM25 behavior, the hybrid mode with pinned local encoder and fixed RRF, conditional activation ('when verified vectors are mounted'), and the fact that no generative model participates. It also reveals that the response includes a query_plan and that hits lack body text. This goes beyond a simple search description, though it omits operational details like rate limits or error behavior.

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?

The description is four sentences, each delivering distinct information: what the tool does, retrieval behavior, response structure, and return constraints. There is no repetition of schema fields and no fluff. It is front-loaded with the core purpose.

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?

Given the tool's complexity (17 parameters, no output schema, no annotations), the description covers key aspects: core functionality, retrieval mechanism, response query_plan, and the limitation of no body text with a pointer to as_of for full state. It does not explain every filter, but the schema does that. It adequately addresses the important behavioral nuances.

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

Parameters3/5

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

Schema coverage is 100% for all 17 parameters, so the schema already provides detailed descriptions. The tool description adds meaning to retrieval_mode ('keyword is deterministic FTS5/BM25; hybrid adds the pinned local encoder') and hints at as_of usage, but does not significantly enhance understanding of the many filter parameters. Baseline of 3 is appropriate.

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?

The description opens with 'Filtered legal search', which clearly identifies the tool as a search over legal documents with filtering. It distinguishes itself from sibling tools (article_history, as_of, diff, etc.) by specifying that it returns hits without body text and that full state is available via as_of.

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

Usage Guidelines4/5

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

The description implicitly guides usage by noting 'Returns hits WITHOUT body text; full state via as_of', which tells the agent to use as_of when full text is needed. It also differentiates retrieval modes (keyword vs hybrid) and clarifies that no generative model participates. However, it does not explicitly enumerate when to prefer this tool over other siblings beyond as_of.

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.

TDQS

A3.8/5.0
Disambiguation4/5

Most tools have clearly distinct purposes, but timeline and article_history both cover historical versions, and as_of and in_force_on both relate to state on a date. Descriptions are detailed enough to resolve overlap, so confusion is limited.

Naming Consistency3/5

All names are lowercase with underscores, but they mix noun forms (coverage, provenance), verb forms (search, diff), and prepositional phrases (as_of, in_force_on, changes_in_period). This is readable but lacks a consistent pattern like verb_noun.

Tool Count5/5

Ten tools is well within the ideal range for a specialized legal research server. Each tool addresses a distinct aspect of temporal legal queries, and none feel redundant or superfluous.

Completeness5/5

The tool set covers search, retrieval, history, citations, coverage gaps, and provenance. It supports both document-level and corpus-level temporal analysis, making it comprehensive for the stated domain of Luxembourg and EU law research.

Resources