Skip to main content
Glama

Ansvar: EU Compliance & Legal Intelligence

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'; (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. 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. 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.

TDQS

A4.9/5.0
Behavior5/5

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

The description adds substantial behavioral context beyond the readOnlyHint and destructiveHint annotations: it explains national transposition swapping, the 'Sources used' audit receipt, meta.render_contract, and the strict requirement to replay hint values to avoid corpus substitution. These are non-obvious behaviors that meaningfully shape how an agent invokes the tool.

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 description is dense but well-organized with numbered addressing forms and inline examples. Every sentence contributes meaningful guidance, though the length is substantial for a tool description. The front-loaded purpose and clear segmentation help mitigate the verbosity.

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 and lack of an output schema, the description fully covers return values (full text, citation metadata), the 'Sources used' section, meta.render_contract, and edge cases like national transposition and non-jurisdictional catalogs. It leaves no obvious gaps for an agent to resolve provision lookup correctly.

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?

Although schema coverage is 100%, the description enriches parameter understanding far beyond the schema. It explains the relationships between law, article, canonical_ref, source_id, and jurisdiction, provides replay rules, and clarifies when each is required or forbidden. This transforms bare parameter definitions into actionable composite usage patterns.

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 'Look up the exact text of a specific legal provision or standards-catalog control,' using a specific verb and resource. It clearly distinguishes from sibling tools by detailing the three addressing forms and explicitly referencing search-row hints, which delineates it from search and other lookups.

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 addressing form, including concrete examples like 'show me Article 5 of GDPR' and the specific shape for NIST corpora. It also states what not to do ('Do not infer source_id from the legal document id') and clarifies when alternative forms apply, such as passing jurisdiction alongside canonical_ref when not embedded.

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

A4.1/5.0
Disambiguation4/5

Most tools have clearly distinct purposes, but a few pairs overlap: get_current_step vs get_progress, search_cve vs search_by_product, and describe_capabilities vs get_my_capabilities. The descriptions provide enough detail to differentiate them, but agents could still occasionally misselect.

Naming Consistency4/5

Names overwhelmingly follow a verb_noun snake_case pattern (get_*, list_*, search_*, start_*, etc.). Minor deviations like 'diff' and 'search' (single-word) and 'batch_search' (compound modifier) are predictable and don't disrupt the overall consistency.

Tool Count3/5

With 30 tools, the server is on the heavier side. The broad scope (legal intelligence, CVE data, full workflow engine) justifies many tools, but some are internal or niche (probe_corpus, recommend_subagents) and could be hidden. It's borderline between well-scoped and excessive.

Completeness4/5

The legal and CVE domains are well-covered: search, provision lookup, validation, diff, coverage, and detailed CVE enrichment. Workflow management is end-to-end. However, get_regulatory_deadlines is referenced by get_regulatory_intelligence_status but not exposed in the toolset, leaving a notable gap.