Skip to main content
Glama

PRIMAMCP

by com.planitprima.lawbster
OverviewDiscussionsAdmin

Look Up Provision by Citation

legal_lookup
Read-onlyIdempotent

Retrieve a specific legal provision by citation (e.g. '§ 823 BGB', 'Art. 6 DSGVO', '§ 280 Abs. 1 BGB'), or a court decision by Aktenzeichen or ECLI (e.g. 'VII ZR 184/14', 'BGH VII ZR 184/14', 'C-184/14', 'ECLI:DE:BGH:2017:050117BVIIZR184.14.0'). Citation order is flexible — '§ 9 DSGVO', 'DSGVO Art. 9', 'Artikel 9 DSGVO' all resolve correctly. is_exact_match reports whether the citation was matched exactly; non-exact results can be a semantic fallback, the first section of an annex, or an uncertain decision match. The result hint explains which case applies; found=true alone does not prove citation identity. Provision text is reassembled where available; content_truncated and the result hint identify incomplete text and its continuation. A decision lookup returns its lead section (Leitsatz); further sections are reachable via legal_get_toc or legal_get_context on the returned norm_id.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
citationYesFull citation string, e.g. '§ 823 BGB' or 'VII ZR 184/14'
languageNoDocument language: 'de' (default, German-language documents from German and EU sources) or 'en' (currently EDPB/EDSA data-protection guidance only). DE and EN are separate corpora — a document published in both languages has one entry per language under the same abbreviation. 'en' selects the English corpus regardless of the answer language; 'edsa' is published mostly in English.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / language / anyOf
      Previous value: -[
-  {
-    "description": "Content language of legal documents.\n\nUses StrEnum so values compare equal to plain strings for\nseamless PostgreSQL/Qdrant compatibility.",
-    "enum": [
-      "de",
-      "en"
-    ],
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "description": "Document language, independent of the language of the answer.",
+    "enum": [
+      "de",
+      "en"
+    ],
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
    • changedInput schema / properties / language / description
      Previous value: -"Corpus language: 'de' (default — the full German + EU corpus) or 'en' (English-language corpus: currently EDPB/EDSA data-protection guidance only; much smaller than 'de'). DE and EN are separate corpora — a document published in both languages has one entry per language under the same abbreviation. 'en' selects the English corpus regardless of the answer language; 'edsa' is published mostly in English."New value: +"Document language: 'de' (default, German-language documents from German and EU sources) or 'en' (currently EDPB/EDSA data-protection guidance only). DE and EN are separate corpora — a document published in both languages has one entry per language under the same abbreviation. 'en' selects the English corpus regardless of the answer language; 'edsa' is published mostly in English."
  2. Changed1 schema field changed
    • changedInput schema / properties / language / description
      Previous value: -"Corpus language: 'de' (default — the full German + EU corpus) or 'en' (English-language corpus: currently EDPB/EDSA data-protection guidance only; much smaller than 'de'). DE and EN are separate corpora — a document published in both languages has one entry per language under the same abbreviation. Set 'en' only when the user explicitly works in English or asks for the English version."New value: +"Corpus language: 'de' (default — the full German + EU corpus) or 'en' (English-language corpus: currently EDPB/EDSA data-protection guidance only; much smaller than 'de'). DE and EN are separate corpora — a document published in both languages has one entry per language under the same abbreviation. 'en' selects the English corpus regardless of the answer language; 'edsa' is published mostly in English."
  3. Changed1 schema field changed
    • addedInput schema / properties / language
      Added value: +{
+  "anyOf": [
+    {
+      "description": "Content language of legal documents.\n\nUses StrEnum so values compare equal to plain strings for\nseamless PostgreSQL/Qdrant compatibility.",
+      "enum": [
+        "de",
+        "en"
+      ],
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Corpus language: 'de' (default — the full German + EU corpus) or 'en' (English-language corpus: currently EDPB/EDSA data-protection guidance only; much smaller than 'de'). DE and EN are separate corpora — a document published in both languages has one entry per language under the same abbreviation. Set 'en' only when the user explicitly works in English or asks for the English version."
+}
  4. Changed1 schema field changed
    • changedInput schema / properties / citation / description
      Previous value: -"Full citation string, e.g. '§ 823 BGB'"New value: +"Full citation string, e.g. '§ 823 BGB' or 'VII ZR 184/14'"
  5. Changed2 schema fields changed
    • addedInput schema / properties / citation / maxLength
      Added value: +200
    • addedInput schema / properties / citation / minLength
      Added value: +1
  6. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already mark this as read-only and idempotent, and the description adds substantial behavioral nuance: flexible citation order, fallback matching semantics, found=true not proving identity, content reassembly/truncation behavior, and decision lead-section handling. This goes far beyond the structured fields and prevents false expectations.

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 front-loaded with the purpose and uses every subsequent sentence to clarify a distinct and important behavior—match semantics, result hints, truncation, or follow-up tools. No filler, repetition, or irrelevant detail appears despite the heavy domain complexity.

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

Completeness5/5

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

For a complex legal lookup tool, the description covers input formats, output semantics (is_exact_match, result hint, content_truncated, norm_id), fallback behavior, and onward navigation to sibling tools. The presence of an output schema further reduces the burden, yet the description still explains the critical non-obvious return-field meanings.

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?

The input schema already fully describes both parameters, so the baseline is 3. The description adds extra value by explaining citation-order flexibility and giving realistic formats for laws, decisions, and ECLI identifiers, while the language parameter remains documented only in the schema. This is a solid enhancement without being exhaustive.

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 a specific verb ('Retrieve') and a clear resource ('a specific legal provision by citation, or a court decision by Aktenzeichen or ECLI'), immediately distinguishing this from broad search tools like legal_search. The included citation examples and the naming of legal_get_toc/legal_get_context for follow-up work reinforce what this tool is and is not.

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 clearly signals 'use this when you have a concrete citation or case number' and even points to legal_get_toc/legal_get_context for continued exploration of a decision. It does not explicitly state when not to use it versus legal_search or legal_lookup_batch, but the emphasis on 'specific' and 'by citation' makes the primary use case unambiguous.

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

All PRIMAMCP toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources