Skip to main content
Glama

Eu Transposition Measures

eu_transposition_measures
Read-onlyIdempotent

For an EU Directive, the national implementing measures (NIM) that each member state has notified to the European Commission — the Publications Office's own transposition tracker, read live from CELLAR. Give a CELEX number (e.g. "32019L1937" for the Whistleblower Directive), the "2019/1937" short form, or a common name (e.g. "Whistleblower Directive", "GDPR"). For a Directive, returns every member state with its measure(s) — title, type of act, document date, notification date, national Official Journal citation — and member states with NO recorded measure are listed explicitly as "none recorded", never dropped. A member state can notify dozens of measures (France has 36 for the Whistleblower Directive, Czechia 80, Croatia 93), mixing the actual transposing act with older provisions CELLAR also links — CELLAR itself does not flag which measure is "the" one, so measures within each state are ordered by how closely a measure's own title echoes the directive's own title (read in whichever language scores best), then by newest document date, which in practice surfaces the real transposing act first or near first; limit_per_state (default 10) then truncates that ranked list, with truncated: true meaning more exist. Where a live Pipeworx national-legislation pack covers that state (Germany/de-gesetze, Austria/at-ris, Italy/it-normattiva, Netherlands/nl-wetten, France/france-legi, Spain/boe-legislacion) the matching pack and tools are named so you can drill into the actual provision text — no SPARQL required anywhere in this chain. A Regulation is answered directly: regulations are not transposed (Article 288 TFEU), so this says that plainly rather than returning an empty list.

Input Schema

NameRequiredDescriptionDefault
directiveYesCELEX number ("32019L1937"), short form ("2019/1937"), or common name ("Whistleblower Directive", "GDPR").
member_stateNoOptional: restrict to one EU member state — English name, ISO2 ("DE"), or ISO3 ("DEU"). Omit to get all 27.
limit_per_stateNoMax measures listed per member state before truncation (default 10, max 50). Some directives have dozens of related national measures per state.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/open-world, but the description adds substantial behavior beyond them: ranking logic by title echo then newest date, the `truncated: true` signal, explicit 'none recorded' entries for states with no measure, and the caveat that CELLAR does not flag the definitive transposing act. This is unusually rich disclosure for a read-only 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 first sentence front-loads the core verb and resource, and every clause is substantive. It is a single very dense paragraph, though — the cardinality examples (France 36, Czechia 80, Croatia 93) are illustrative rather than essential and the ranking explanation is verbose.

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?

With no output schema, the description carries the return-shape burden and does so: per-state measure fields (title, act type, document date, notification date, national OJ citation), 'none recorded' states, and the truncation flag. Nothing needed to call it or interpret the result is missing.

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 baseline is 3, but the description adds real semantics: it explains that `limit_per_state` truncates a ranked list (default 10) and that the truncation is signaled by `truncated: true`, which is not visible in the schema. It also reinforces the accept-all-27 default for omitting `member_state`.

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?

States a specific verb+resource+scope: national implementing measures per member state for an EU Directive, read live from CELLAR. It also explicitly contrasts with sibling approaches (Pipeworx national-legislation packs, 'no SPARQL required anywhere in this chain'), so an agent can distinguish it from cellar_sparql/cellar_search_works.

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?

Gives accepted input forms with concrete examples (CELEX, short form, common name), states the exclusion that Regulations are answered directly rather than returning an empty list, and names the drill-down path when a national pack covers the state. That is when-to-use, when-not, and alternatives in one pass.

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.