Skip to main content
Glama

Ansvar: EU Compliance & Legal Intelligence

by eu.ansvar
OverviewDiscussionsAdmin

Get Provision

get_provision
Read-only

Look up the exact text of a specific legal provision or standards-catalog control. Three addressing forms: (1) jurisdiction + law + article — use this when someone asks 'show me Article 5 of GDPR', 'what does Section 12 of the Swedish Work Environment Act say', or 'read me the text of DORA Article 11'. A U.S. federal regulation is addressed by its CFR citation: get_provision(jurisdiction='US', law='45 CFR', article='164.410') (also '45 C.F.R.' + '§ 164.410', or law='45 CFR Part 46' + article='Part 46' for a part) reaches the one corpus that serves that CFR part; (2) canonical_ref — the exact ref a search row's citation.lookup hint advertises (e.g. get_provision(canonical_ref='loi-2018-07-30:art-64', jurisdiction='BE')): the gateway decomposes it and resolves the same way. Pass jurisdiction alongside canonical_ref when the ref does not embed one (relayed hints already include it). (3) law as a bare corpus/source id + article as the native control/entity id, NO jurisdiction — for non-jurisdictional standards catalogs (e.g. get_provision(law='nist-800-53', article='AC-5') for NIST SP 800-53, and the same shape for nist-csf-2, nist-800-82r3, nist-ai-rmf, nist-ssdf-800-218): a search row's citation.lookup hint for these corpora already advertises this exact shape — replay it verbatim. For a national statute you have not seen in a search row, search first and replay that row's citation.lookup; a law name resolves only where Ansvar has an alias for that name. Returns the full provision text with citation metadata. A member-state jurisdiction plus an EU framework article that has a verified national transposition returns the NATIONAL transposing provision, with meta.transposition naming the swap; pass jurisdiction='EU' for the framework text itself. Where no such mapping applies, the same field may instead carry a typed disclosure describing Ansvar's verified coverage for that pair. When a national transposition IS served, the CELEX and instrument name that response reports are themselves valid law input in that jurisdiction — replay either. When a law name matches several documents or does not resolve (near matches, reason_code=law_name_unresolved), each meta.ambiguous_candidates item is an executable get_provision retry: retry_args contains jurisdiction, law (the chassis doc_id), and the original article, or jurisdiction plus canonical_ref when the resolver supplied one; retry_kind identifies which addressing form it uses, and label carries the served document title (up to 120 characters, empty when unavailable). The response ends with a 'Sources used' section — a markdown table carrying the audit receipt for each returned row, or a labelled zero-result note — and meta.render_contract carries the versioned evidence-curation contract for reproducing source attributions when the answer is rendered. Search lookup hints may include source_id, the exact routed corpus that served the row. It is valid only with the hint's nonblank canonical_ref; law and article must remain empty. Replay the whole args object unchanged so a document present in multiple corpora cannot be substituted. Do not infer source_id from the legal document id.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
lawNoEither the instrument the provision belongs to — a framework id ('GDPR', 'DORA') or the corpus's own law identifier — or, for a non-jurisdictional standards catalog, the bare corpus source id ('nist-800-53', 'nist-csf-2').
articleNoArticle or section number within the instrument ('5', '5(1)(a)'), or the native control id when law is a bare standards-catalog source id ('AC-5').
source_idNoExact routed corpus id from a search row's citation.lookup hint. Valid only with that hint's nonblank canonical_ref; law and article must remain empty. When present, that corpus's exact hit or miss is authoritative: the gateway does not fall through to a sibling corpus. Replay the hint value; do not infer it from the legal document id.
jurisdictionNoISO-2 code of the jurisdiction that owns the provision, such as EU, SE, or BE. Required for the jurisdiction+law+article form, and alongside a canonical_ref that does not embed one. Leave empty for the bare-source-id form (law='nist-800-53').
canonical_refNoThe exact reference a search row's citation.lookup hint advertises, such as 'loi-2018-07-30:art-64'. Replay it verbatim instead of decomposing it yourself; the gateway resolves it the same way as jurisdiction+law+article.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / source_id
      Added value: +{
+  "default": "",
+  "description": "Exact routed corpus id from a search row's citation.lookup hint. Valid only with that hint's nonblank canonical_ref; law and article must remain empty. When present, that corpus's exact hit or miss is authoritative: the gateway does not fall through to a sibling corpus. Replay the hint value; do not infer it from the legal document id.",
+  "title": "Source Id",
+  "type": "string"
+}
  2. Changed4 schema fields changed
    • addedInput schema / properties / article / description
      Added value: +"Article or section number within the instrument ('5', '5(1)(a)'), or the native control id when law is a bare standards-catalog source id ('AC-5')."
    • addedInput schema / properties / canonical_ref / description
      Added value: +"The exact reference a search row's citation.lookup hint advertises, such as 'loi-2018-07-30:art-64'. Replay it verbatim instead of decomposing it yourself; the gateway resolves it the same way as jurisdiction+law+article."
    • addedInput schema / properties / jurisdiction / description
      Added value: +"ISO-2 code of the jurisdiction that owns the provision, such as EU, SE, or BE. Required for the jurisdiction+law+article form, and alongside a canonical_ref that does not embed one. Leave empty for the bare-source-id form (law='nist-800-53')."
    • addedInput schema / properties / law / description
      Added value: +"Either the instrument the provision belongs to — a framework id ('GDPR', 'DORA') or the corpus's own law identifier — or, for a non-jurisdictional standards catalog, the bare corpus source id ('nist-800-53', 'nist-csf-2')."
  3. First observed

TDQS

A5/5.0
Behavior5/5

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

Annotations declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, which already signal a safe read operation. The description adds substantial behavioral context beyond that: the national-transposition swap (returning the national provision and naming it in meta.transposition), the typed disclosure when no mapping applies, the ambiguous-candidates retry mechanism with retry_args and retry_kind, the 'Sources used' markdown table, and the meta.render_contract for evidence curation. It even cautions against inferring source_id to prevent substitution across corpora. No contradictions with annotations.

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?

Although the description is long, every sentence serves a purpose and the structure is exemplary. It starts with the core purpose, then systematically walks through the three addressing forms with examples, then covers edge cases (transposition, ambiguity, source_id constraints), and ends with response details. There is no filler; the length is justified by the tool's complexity and the need to prevent misuse. It is front-loaded with the most critical information.

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?

Given the tool's complexity—three addressing forms, national transposition logic, ambiguous candidate retries, source_id constraints, and response metadata—the description is remarkably complete. It covers what the tool returns (full text, metadata, sources-used section, render contract) even though there is no output schema. It also anticipates common failure modes (law_name_unresolved, near matches) and tells the agent exactly how to recover. Nothing an agent needs to call this tool correctly is missing.

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

Parameters5/5

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

The input schema already has descriptions for all five parameters, but the tool description enriches them significantly. It explains how the parameters combine into three distinct addressing forms, gives exact examples for each, clarifies the role of jurisdiction in canonical_ref (pass it when the ref does not embed one), and imposes validity rules on source_id and the bare-source-id form. This is precisely the kind of semantic depth that helps an agent invoke the tool correctly, exceeding the baseline set by a 100% coverage schema.

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 clear, specific statement of the tool's function: 'Look up the exact text of a specific legal provision or standards-catalog control.' It immediately distinguishes three addressing forms and gives concrete examples (e.g., 'Article 5 of GDPR', '45 CFR § 164.410', 'nist-800-53 AC-5'). This goes far beyond a vague purpose and clearly separates it from sibling tools like search, which finds rows rather than resolving exact text.

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?

The description provides explicit when-to-use guidance for each of the three addressing forms, including when to prefer search first ('For a national statute you have not seen in a search row, search first and replay that row's citation.lookup'). It also states when not to use certain parameters (e.g., 'source_id... is valid only with the hint's nonblank canonical_ref; law and article must remain empty') and how to handle ambiguity. No other tool is confused with this one.

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

All Ansvar: EU Compliance & Legal Intelligence 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