Skip to main content
Glama
Sign In

LibreJustice

by fr.librejustice
OverviewDiscussionsAdmin

Server Details

Search French-language and European case law and French legal texts (codes, statutes, treaties).

Ownership verified
Status
Healthy
Uptime
99.9% over 77 days
OAuth
Works in Glama
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
Repository
librejustice/librejustice
GitHub Stars
30
Server Listing
LibreJustice

TDQS

A4.3/5.0

Scored across 4 tools

Disambiguation5/5

The set splits cleanly along two axes: resource (decisions vs. norms) and operation (search vs. fetch), giving four non-overlapping tools. Each description explicitly states its role and even cross-references the sibling tool to chain into, leaving no misselection risk.

Naming Consistency5/5

All four names follow a strict verb_noun pattern: get_decision, get_norm, search_decisions, search_norms. The singular/plural split (get one item vs. search many) is a deliberate, readable convention rather than an inconsistency.

Tool Count5/5

Two entity types times two operations (find and read) yields exactly four tools, each earning its place. Nothing extraneous is exposed and nothing obvious is merged away; the surface matches the domain precisely.

Completeness4/5

Read-only retrieval is fully covered: both decisions and norms can be searched and fetched, with date-versioning, chronology, and facets handled inside the existing tools. The one gap is that `commentaries` documents are surfaced as links from get_decision but no tool retrieves them, so an agent hits a dead end there.

Available Tools

4 tools
get_decisionGet DecisionA
Read-onlyIdempotent
Inspect

Fetch the full text and metadata of a decision by its url. The text carries inline markdown links to cited articles (/norm/, open with get_norm) and cited decisions (/decision/, open with get_decision); a citation spanning several articles (« articles 3 à 6 », « et suivants ») links its first article and appends the others as labelled links right after the span. case_chronology lists the prior AND subsequent decisions of the same case (appeal, pourvoi, renvoi), each with its solution. commentaries lists documents around the decision (the court's summary, conclusions, reports…). official_url is the decision at its official publisher, proof of its authenticity.

NameRequiredDescriptionDefault
urlYesA librejustice.fr decision URL, from a search_decisions hit or an inline citation link; search_decisions first if you have neither.

Output Schema

NameRequiredDescription
urlYes
dateNo
seatNo
textYes
titleYes
officeNo
solutionNo
procedureNo
publicationNo
commentariesNo
legal_domainNo
official_urlNo
docket_numbersNo
case_chronologyNo
jurisdiction_codeNo
jurisdiction_typeYes

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds non-obvious behavior an agent could not infer: text arrives as markdown with inline citation links, multi-article citations link only the first article and append the rest as labelled links, and the payload carries case_chronology, commentaries and official_url.

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 core action is front-loaded in the first clause and every following sentence describes a distinct part of the returned payload. The citation-spanning sentence is dense and slightly hard to parse on first read, but it carries information not available elsewhere.

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?

An output schema exists, so the description need not enumerate return fields; it nonetheless characterizes the shape of the text and the auxiliary sections. Combined with the schema's URL-provenance guidance, an agent has everything needed to call this correctly and act on the result.

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?

There is a single parameter at 100% schema description coverage, and the schema itself explains provenance (a search_decisions hit or an inline citation link) and the fallback to search_decisions. The description only says 'by its `url`', adding no format or validation detail beyond the schema, so baseline 3 applies.

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 and resource ('Fetch the full text and metadata of a decision') and pins the identifier ('by its `url`'). It also implicitly separates itself from get_norm by explaining that /norm/ links go to get_norm while /decision/ links come back here, so an agent can route between the two without opening schemas.

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 gives concrete trigger conditions: use it to follow inline /decision/ citation links inside a decision's text, and the citation-spanning rule tells the agent which link to click when a reference covers several articles. It does not state when to prefer search_decisions instead, though the input schema's parameter text covers that ('search_decisions first if you have neither').

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

get_normGet NormA
Read-onlyIdempotent
Inspect

Fetch a legal text, or one of its articles, as it stood on a given date. Returns the version in force at as_of (omit for today): full text, status, validity dates, and the timeline of all versions: say which version you quote. The text carries inline markdown links to cross-referenced articles (/norm/, open with get_norm; when served at a date, the links point to the same date). commentaries links out to commentary anchored on the article. number absent means you hold the whole text; the url of an article's section, or of a section entry of articles, returns all its articles at once.

NameRequiredDescriptionDefault
urlNoA librejustice.fr article URL `/norm/{jurisdiction}/{code}/{article}`: take it from a search_norms hit or an inline citation link, or compose it: {jurisdiction} is the enacting state as ISO 3166-1 alpha-2 lowercase ("fr", "be"), "eu" for the Union, its treaties included, "intl" for a treaty signed outside it (the ECHR, a bilateral accord), {code} is the code slug ("code-civil", as in facets.legal_instrument), {article} the lowercase article key ("l761-1" for L. 761-1, "1240" for 1240). `/norm/{jurisdiction}/{code}` alone addresses the text itself, which is how a text with no articles (circulaire, publication decree) is read.
codeNoCode slug, when you hold the code and the article apart rather than as a url ("code-civil"). Alone, addresses the text itself.
as_ofNoConsultation date (YYYY-MM-DD): returns the version in force at that date. Omit for the version currently in force.
articleNoLowercase article key, alongside `code` ("l761-1" for L. 761-1, "1240" for 1240).
text_idNoLégifrance id: an article (LEGIARTI, JORFARTI, KALIARTI), a text (LEGITEXT, JORFTEXT) or a section (LEGISCTA); or a BOFiP id (BOI-…), with `article` for one paragraph.

Output Schema

NameRequiredDescription
urlYes
codeYes
dateNo
noteNo
textNo
titleYes
numberNo
statusNo
omittedNo
sectionNo
articlesNo
valid_toNo
versionsYes
source_urlNo
valid_fromNo
modified_byNoTexts that created, modified or repealed this article.
commentariesNo
article_countNo
legislative_historyNo

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already establish that this is a read-only, idempotent, non-destructive operation. The description adds substantial behavioral context beyond that: it returns the version in force at `as_of`, includes status, validity dates, and a full version timeline, and explains that inline links preserve the served date. It does not discuss auth or rate limits, but the added retrieval behavior is meaningful.

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 purpose is front-loaded and most sentences add useful retrieval or citation context. The final sentence is dense and references response fields such as `number` and `commentaries` without clearly framing them as output fields, which slightly harms readability.

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?

The tool has an output schema and rich annotations, so the description does not need to explain return values in full. It still covers the key behavior around dated versions, inline links, and section-level retrieval. The main gap is that it does not explain precedence when multiple optional address parameters are supplied.

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 description coverage is 100%, so the schema already carries the main burden of explaining each parameter. The description adds some semantic detail about `as_of` and section URLs returning all articles, but it does not clarify precedence among `url`, `code`+`article`, and `text_id`, nor how those addressing modes combine.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Fetch a legal text, or one of its articles, as it stood on a given date.' That is clear enough to distinguish it from search_norms and decision tools, but it does not explicitly name its siblings to sharpen the boundary.

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

Usage Guidelines3/5

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

It gives useful usage cues: omit `as_of` for today, and open inline cross-referenced articles with get_norm. However, it never says when to use search_norms first or when to prefer get_decision, so the agent must infer the workflow from context.

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

search_decisionsSearch DecisionsA
Read-onlyIdempotent
Inspect

Search decisions by meaning and keywords combined. Returns a shortlist: title, url, an overview (ai_summary: AI-written summary of what the decision is about, the court's own words in « »; or snippet: the verbatim passage where your keywords matched) and metadata; get_decision reads the full text. Put constraints in the structured filters (jurisdiction, dates, articles, codes), keep the query for the legal issue. Values within one filter are OR'd; different filters are AND'd. The response carries a facets block: per filter name, a map of filter value to decision count under the current query. Reuse those keys verbatim to refine. Hit metadata fields carry the same tokens under the same names: a hit's seat, legal_domain or solution passes back verbatim into the matching filter.

NameRequiredDescriptionDefault
modeNo'auto' is the right choice in almost all cases. auto: automatically switches among 'semantic', 'lexical' and 'reference'. semantic: meaning + keyword hybrid, quoted phrases filter presence. lexical: keyword-only, every word required, quoted phrases exact, ET / AND / OU / OR / SAUF / NOT / PROCHE5 / NEAR5 / répar*. reference: lookup by identity, on the docket number, the ECLI, the case name, or the court and the date.auto
seatNoRestrict to one or more seats, as a dotted path from the legal order down to the room: "FR" (an order), "FR.CA" (a type), "FR.CA.PARIS" (a court), "FR.CC.C1_CIVILE", "FR.CA.PARIS.P5.C3", "FR.TJ.PARIS.REFERES" (a room), "EU.CJUE", "INTL.CEDH". A path matches itself and everything below it, so start at the order and go deeper. Types: TJ (tribunal judiciaire), CA (cour d'appel), CC (Cour de cassation), TCOM (tribunal des activités économiques), CPH (conseil de prud'hommes), TA (tribunal administratif), CAA (cour administrative d'appel), CE (Conseil d'État), CNDA (asylum), CONSTIT (Conseil constitutionnel), TC (Tribunal des conflits), CNIL (sanctions), CEDH and CJUE (European courts). Take the paths from facets.seat.
sortNoResult ordering. Use 'relevance' (default) unless the user wants chronological order. A date order excludes mode 'semantic'.relevance
limitNoMaximum number of results (default 10).
queryYesThe primary input, in the language of the decisions sought: a question or descriptive keywords on a legal issue (« licenciement discrimination syndicale charge de la preuve »), with quoted phrases for a name or a precise formula (« "Société Générale" responsabilité du banquier »); a boolean formula (« "force majeure" ET épidémie SAUF grippe »); or a reference (« 21PA01295 », « CE 13 juillet 2016 », « Czabaj »).
officeNoFilter by specialised judge/office (JLD, JAF, JCP, JEX, juge des enfants, premier président, magistrat désigné). Absent value = ordinary bench.
date_toNoLatest decision date, inclusive (YYYY-MM-DD).
solutionNoFilter by the ruling of the operative part (référentiel solution). REJET / IRRECEVABILITE / DESISTEMENT / NON_LIEU_A_STATUER are procedural or negative endings; CONFIRMATION / INFIRMATION* / REFORMATION are appeal outcomes; CASSATION* is cassation-specific; ANNULATION covers administrative annulment; SATISFACTION_TOTALE / SATISFACTION_PARTIELLE cover first-instance civil rulings granting the claim.
ai_rerankNoWhen enabled (default), reorders results by actual relevance to the query using an LLM reranker. Keep on for agentic use, shortlist quality is significantly higher. Cost: a few seconds of extra latency. Disable only for high-rate exploratory searches where latency matters more than ranking quality.
date_fromNoEarliest decision date, inclusive (YYYY-MM-DD).
procedureNoFilter by procedural track (référés, QPC, EU referral, révision, tierce opposition…). Absent value = ordinary contentious procedure.
publicationNoFilter by publication, at the grain the Cour de cassation itself uses (any-of, membership is multiple: a decision matches every value whose code it carries). Judicial order: PUBLIE_RAPPORT (annual report, the strongest signal), PUBLIE_BULLETIN, LETTRE_CHAMBRE, COMMUNIQUE, INEDIT_BULLETIN. Administrative order: PUBLIE_LEBON, MENTIONNE_LEBON, INEDIT_LEBON. Lower courts carry no publication statement and match no value.
legal_domainNoFilter by legal domain (curated domain tree): 9 roots and their leaves (e.g. CIVIL_DROIT_LOCATIF). Selecting a root also matches all its leaves.
legal_articleNoRestrict to decisions citing a specific article of a specific code, as a composite key "<instrument>|<article>" where <instrument> is a slug or an exact text name, resolved like legal_instrument (e.g. "code-civil|1240", "code-de-justice-administrative|L761-1"). The instrument prefix is required: the same article number exists in several codes.
legal_instrumentNoRestrict to decisions citing one or more given codes or statutes. Accepts a slug from facets.legal_instrument (e.g. "code-civil") or an exact text name resolved server-side (e.g. "Code civil").

Output Schema

NameRequiredDescription
hitsYes
queryYes
totalYes
facetsNo
pinnedNo

TDQS

A4.7/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, non-destructive behavior, but the description adds meaningful context: it returns a shortlist with ai_summary/snippet and metadata, carries a facets block, and supports OR within filters and AND across filters. It does not contradict the annotations. Minor gap: it does not mention rate limits or latency beyond the schema's ai_rerank note.

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 dense but front-loaded: purpose first, then return shape, alternative, filtering rules, facets, and token reuse. Every sentence adds operational guidance for a complex 15-parameter search tool. No filler or repetition.

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 15 parameters, full schema coverage, an output schema, and safe read-only annotations, the description supplies the remaining high-value context: what the shortlist contains, how to refine with facets, how filters combine, and when to use get_decision. Nothing essential for correct invocation 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 the baseline is 3, but the description adds value beyond the schema by explaining OR-within-filter / AND-across-filter semantics and that facets keys and hit metadata tokens can be passed back verbatim into matching filters. It does not try to restate every parameter, which is appropriate given full schema coverage.

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 and resource: searches decisions by meaning and keywords combined. It also distinguishes the result from the sibling get_decision by explaining that get_decision reads the full text. An agent can tell what this tool does and how it differs from the directly related sibling.

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?

Explicitly says to put constraints in structured filters and keep the query for the legal issue, and names get_decision as the full-text alternative. It also explains how to refine using facets and that keys can be reused verbatim. This gives clear when-to-use and alternative guidance.

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

search_normsSearch NormsA
Read-onlyIdempotent
Inspect

Find legal articles from their subject, their wording, or an article number with no code named; returns a shortlist with highlighted snippets and the exact total. Query in French, descriptive terms (« délai de recours contentieux refus implicite »); put the code in the code filter (slug or exact name), keep the query for the subject. With no query, hits are whole texts, the most recently changed first. The response carries a facets block (code, jurisdiction): per filter name, a map of filter value to article count, reuse those keys verbatim to refine. Chain a hit into get_norm with its url, plus as_of when the dispute is governed by an earlier version.

NameRequiredDescriptionDefault
codeNoRestrict to one code/text by its URL slug ("code-civil", as in facets.code) or exact name. Omit to search the whole navigable referential.
as_ofNoConsultation date (YYYY-MM-DD): searches the versions valid at that date (point-in-time, same semantics as get_norm). Omit to search the versions currently in force.
limitNoMaximum number of results (default 10).
queryNoFrench query over legal articles. Matches article titles (boosted) and bodies; alias expansion handles acronyms and usual names.
valid_fromNoEarliest entry into force (YYYY-MM-DD) of the versions served, which are those in force at `as_of`, else today. A text's publication counts as its first version.
jurisdictionNoFilter by country/legal order, as an ISO 3166 alpha-2 country code: "FR" (France, the bulk of the corpus) or a foreign code ("SN", "DZ", "MA", "VN", "PE", …); plus "EU" for EU law and "INTL" for treaties/international law. A dotted path narrows to a type of text: "FR.LOI", "FR.DECRET", "EU.DIRECTIVE", "INTL.TREATY", as in facets.jurisdiction.

Output Schema

NameRequiredDescription
hitsYes
queryYes
totalYes
facetsYes
pinnedNo

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already cover read-only, idempotent, non-destructive, closed-world behavior, and the description adds valuable operational context: highlighted snippets, exact `total`, facets structure, sorting behavior with no query, and version semantics via `as_of`/`valid_from`.

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 dense but front-loaded with purpose and return shape, then proceeds through query guidance, no-query behavior, facets, and chaining. Every sentence contributes actionable information for selecting or invoking the tool.

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 an output schema present, annotations covering safety, and full schema descriptions, the description completes the picture by explaining query strategy, filter interaction, response facets, and next-step chaining into get_norm.

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 the schema already documents all six parameters in detail. The description still adds useful semantics around French query phrasing, using `code` instead of mixing code names into `query`, no-query behavior, and reusing facet keys verbatim for refinement.

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 states a specific action and resource: finding legal articles by subject, wording, or article number, and returning a ranked shortlist with snippets and an exact total. It also distinguishes this discovery step from get_norm, which is used when chaining a hit into a specific norm.

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?

It explicitly tells the agent to use French descriptive queries, place code lookups in the `code` filter, keep subject terms in `query`, and expect whole-text hits when `query` is omitted. It also names get_norm as the next step with `url` and `as_of` for earlier-version disputes.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool update
    • Changedsearch_decisions1 field changed
      • changedInput schema / properties / office / anyOf
        Previous value: -[
-  {
-    "items": {
-      "enum": [
-        "JLD",
-        "JAF",
-        "JCP",
-        "JEX",
-        "JUGE_ENFANTS",
-        "PREMIER_PRESIDENT",
-        "MAGISTRAT_DESIGNE",
-        "PRESIDENT_SECTION_CONTENTIEUX",
-        "JUGE_EXPROPRIATION"
-      ],
-      "type": "string"
-    },
-    "type": "array"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "items": {
+      "enum": [
+        "JLD",
+        "JAF",
+        "JCP",
+        "JEX",
+        "JUGE_ENFANTS",
+        "PREMIER_PRESIDENT",
+        "MAGISTRAT_DESIGNE",
+        "PRESIDENT_SECTION_CONTENTIEUX",
+        "JUGE_EXPROPRIATION",
+        "MISE_EN_ETAT"
+      ],
+      "type": "string"
+    },
+    "type": "array"
+  },
+  {
+    "type": "null"
+  }
+]
  2. 2 tool updates
    • Changedget_decision1 field changed
      • removedOutput schema / properties / commentaries / items / properties / access
        Removed value: -{
-  "anyOf": [
-    {
-      "enum": [
-        "libre",
-        "abonnes"
-      ],
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
    • Changedget_norm1 field changed
      • removedOutput schema / properties / commentaries / items / properties / access
        Removed value: -{
-  "anyOf": [
-    {
-      "enum": [
-        "libre",
-        "abonnes"
-      ],
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
  3. 2 tool updates
    • Changedsearch_decisions1 field changed
      • changedInput schema / properties / seat / description
        Previous value: -"Restrict to one or more seats, as a dotted path from the court type down to the room: \"CA\" (a whole type), \"CA.PARIS\" and \"TJ.BORDEAUX\" (one court), \"CC.C1_CIVILE\", \"CA.PARIS.P5.C3\", \"TJ.LYON.SOCIALE\", \"TJ.PARIS.REFERES\", \"TA.MARSEILLE.C5\" (one room). A path matches itself and everything below it, so start at the type and go deeper. Types: TJ (tribunal judiciaire), CA (cour d'appel), CC (Cour de cassation), TCOM (tribunal des activités économiques), CPH (conseil de prud'hommes), TA (tribunal administratif), CAA (cour administrative d'appel), CE (Conseil d'État), CNDA (asylum), CONSTIT (Conseil constitutionnel), TC (Tribunal des conflits), CNIL (sanctions), CEDH and CJUE (European courts). Take the paths from facets.seat."New value: +"Restrict to one or more seats, as a dotted path from the legal order down to the room: \"FR\" (an order), \"FR.CA\" (a type), \"FR.CA.PARIS\" (a court), \"FR.CC.C1_CIVILE\", \"FR.CA.PARIS.P5.C3\", \"FR.TJ.PARIS.REFERES\" (a room), \"EU.CJUE\", \"INTL.CEDH\". A path matches itself and everything below it, so start at the order and go deeper. Types: TJ (tribunal judiciaire), CA (cour d'appel), CC (Cour de cassation), TCOM (tribunal des activités économiques), CPH (conseil de prud'hommes), TA (tribunal administratif), CAA (cour administrative d'appel), CE (Conseil d'État), CNDA (asylum), CONSTIT (Conseil constitutionnel), TC (Tribunal des conflits), CNIL (sanctions), CEDH and CJUE (European courts). Take the paths from facets.seat."
    • Changedsearch_norms1 field changed
      • changedInput schema / properties / jurisdiction / description
        Previous value: -"Filter by country/legal order, as an ISO 3166 alpha-2 country code: \"FR\" (France, the bulk of the corpus) or a foreign code (\"SN\", \"DZ\", \"MA\", \"VN\", \"PE\", …); plus \"UE\" for EU law and \"INTL\" for treaties/international law. A dotted path narrows to a type of text: \"FR.LOI\", \"FR.DECRET\", \"UE.DIRECTIVE\", \"INTL.TREATY\", as in facets.jurisdiction."New value: +"Filter by country/legal order, as an ISO 3166 alpha-2 country code: \"FR\" (France, the bulk of the corpus) or a foreign code (\"SN\", \"DZ\", \"MA\", \"VN\", \"PE\", …); plus \"EU\" for EU law and \"INTL\" for treaties/international law. A dotted path narrows to a type of text: \"FR.LOI\", \"FR.DECRET\", \"EU.DIRECTIVE\", \"INTL.TREATY\", as in facets.jurisdiction."
  4. 2 tool updates
    • Changedsearch_decisions1 field changed
      • changedInput schema / properties / seat / description
        Previous value: -"Restrict to one or more seats, as a dotted path from the court type down to the room: \"CA\" (a whole type), \"CA.PARIS\" and \"TJ.BORDEAUX\" (one court), \"CC.C1_CIVILE\", \"CA.PARIS.P5.C3\", \"TJ.LYON.SOCIALE\", \"TJ.PARIS.REFERES\", \"TA.MARSEILLE.C5\" (one room). A path matches itself and everything below it, so start at the type and go deeper. Types: TJ (tribunal judiciaire), CA (cour d'appel), CC (Cour de cassation), TCOM (tribunal des activités économiques), TA (tribunal administratif), CAA (cour administrative d'appel), CE (Conseil d'État), CNDA (asylum), CONSTIT (Conseil constitutionnel), TC (Tribunal des conflits), CNIL (sanctions), CEDH and CJUE (European courts). Take the paths from facets.seat."New value: +"Restrict to one or more seats, as a dotted path from the court type down to the room: \"CA\" (a whole type), \"CA.PARIS\" and \"TJ.BORDEAUX\" (one court), \"CC.C1_CIVILE\", \"CA.PARIS.P5.C3\", \"TJ.LYON.SOCIALE\", \"TJ.PARIS.REFERES\", \"TA.MARSEILLE.C5\" (one room). A path matches itself and everything below it, so start at the type and go deeper. Types: TJ (tribunal judiciaire), CA (cour d'appel), CC (Cour de cassation), TCOM (tribunal des activités économiques), CPH (conseil de prud'hommes), TA (tribunal administratif), CAA (cour administrative d'appel), CE (Conseil d'État), CNDA (asylum), CONSTIT (Conseil constitutionnel), TC (Tribunal des conflits), CNIL (sanctions), CEDH and CJUE (European courts). Take the paths from facets.seat."
    • Changedsearch_norms6 fields changed
      • removedInput schema / properties / date_from
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Earliest text date, inclusive (YYYY-MM-DD): its signature or adoption, else its publication."
-}
      • removedInput schema / properties / date_to
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Latest text date, inclusive (YYYY-MM-DD)."
-}
      • addedInput schema / properties / valid_from
        Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Earliest entry into force (YYYY-MM-DD) of the versions served, which are those in force at `as_of`, else today. A text's publication counts as its first version."
+}
      • removedOutput schema / properties / hits / items / properties / date
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "format": "date"
-}
      • addedOutput schema / properties / hits / items / properties / valid_from
        Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "format": "date"
+}
      • addedOutput schema / properties / hits / items / properties / valid_to
        Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "format": "date"
+}
  5. 1 tool update
    • Changedsearch_norms5 fields changed
      • addedInput schema / properties / date_from
        Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Earliest text date, inclusive (YYYY-MM-DD): its signature or adoption, else its publication."
+}
      • addedInput schema / properties / date_to
        Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Latest text date, inclusive (YYYY-MM-DD)."
+}
      • changedInput schema / properties / jurisdiction / description
        Previous value: -"Filter by country/legal order, as an ISO 3166 alpha-2 country code: \"FR\" (France, the bulk of the corpus) or a foreign code (\"SN\", \"DZ\", \"MA\", \"VN\", \"PE\", …); plus \"UE\" for EU law and \"INTL\" for treaties/international law."New value: +"Filter by country/legal order, as an ISO 3166 alpha-2 country code: \"FR\" (France, the bulk of the corpus) or a foreign code (\"SN\", \"DZ\", \"MA\", \"VN\", \"PE\", …); plus \"UE\" for EU law and \"INTL\" for treaties/international law. A dotted path narrows to a type of text: \"FR.LOI\", \"FR.DECRET\", \"UE.DIRECTIVE\", \"INTL.TREATY\", as in facets.jurisdiction."
      • removedInput schema / required
        Removed value: -[
-  "query"
-]
      • addedOutput schema / properties / hits / items / properties / date
        Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "format": "date"
+}
  6. 4 tool updates
    • Changedget_decision17 fields changed
      • removedOutput schema / properties / caseChronology
        Removed value: -{
-  "items": {
-    "additionalProperties": false,
-    "properties": {
-      "current": {
-        "type": "boolean"
-      },
-      "linkToNext": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null
-      },
-      "solution": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null
-      },
-      "title": {
-        "type": "string"
-      },
-      "url": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null
-      }
-    },
-    "required": [
-      "title",
-      "current"
-    ],
-    "type": "object"
-  },
-  "type": "array"
-}
      • addedOutput schema / properties / case_chronology
        Added value: +{
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "current": {
+        "type": "boolean"
+      },
+      "link_to_next": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null
+      },
+      "solution": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null
+      },
+      "title": {
+        "type": "string"
+      },
+      "url": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null
+      }
+    },
+    "required": [
+      "title",
+      "current"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}
      • removedOutput schema / properties / commentaires
        Removed value: -{
-  "items": {
-    "additionalProperties": false,
-    "properties": {
-      "access": {
-        "anyOf": [
-          {
-            "enum": [
-              "libre",
-              "abonnes"
-            ],
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null
-      },
-      "author": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null
-      },
-      "date": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null,
-        "format": "date"
-      },
-      "issue": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null
-      },
-      "kind": {
-        "enum": [
-          "conclusions",
-          "note"
-        ],
-        "type": "string"
-      },
-      "pages": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null
-      },
-      "publisher": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null
-      },
-      "title": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null
-      },
-      "url": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null
-      },
-      "volume": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null
-      }
-    },
-    "required": [
-      "kind"
-    ],
-    "type": "object"
-  },
-  "type": "array"
-}
      • addedOutput schema / properties / commentaries
        Added value: +{
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "access": {
+        "anyOf": [
+          {
+            "enum": [
+              "libre",
+              "abonnes"
+            ],
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null
+      },
+      "author": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null
+      },
+      "body": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null
+      },
+      "date": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "format": "date"
+      },
+      "issue": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null
+      },
+      "kind": {
+        "enum": [
+          "summary",
+          "conclusions",
+          "note"
+        ],
+        "type": "string"
+      },
+      "pages": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null
+      },
+      "publisher": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null
+      },
+      "title": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null
+      },
+      "url": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null
+      },
+      "volume": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null
+      }
+    },
+    "required": [
+      "kind"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}
      • addedOutput schema / properties / date
        Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "format": "date"
+}
      • removedOutput schema / properties / dateLecture
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "format": "date"
-}
      • removedOutput schema / properties / docketNumbers
        Removed value: -{
-  "anyOf": [
-    {
-      "items": {
-        "type": "string"
-      },
-      "type": "array"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • addedOutput schema / properties / docket_numbers
        Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}
      • removedOutput schema / properties / jurisdictionCode
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • removedOutput schema / properties / jurisdictionType
        Removed value: -{
-  "type": "string"
-}
      • addedOutput schema / properties / jurisdiction_code
        Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}
      • addedOutput schema / properties / jurisdiction_type
        Added value: +{
+  "type": "string"
+}
      • removedOutput schema / properties / legalDomain
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • addedOutput schema / properties / legal_domain
        Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}
      • removedOutput schema / properties / officialUrl
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • addedOutput schema / properties / official_url
        Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}
      • changedOutput schema / required
        Previous value: -[
-  "title",
-  "url",
-  "jurisdictionType",
-  "text"
-]New value: +[
+  "title",
+  "url",
+  "jurisdiction_type",
+  "text"
+]
    • Changedget_norm36 fields changed
      • addedInput schema / properties / as_of
        Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Consultation date (YYYY-MM-DD): returns the version in force at that date. Omit for the version currently in force."
+}
      • removedInput schema / properties / date
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Consultation date (YYYY-MM-DD): returns the version in force at that date. Omit for the version currently in force."
-}
      • removedInput schema / properties / textId
        Removed value: -{
-  "description": "Légifrance id: an article (LEGIARTI, JORFARTI, KALIARTI), a text (LEGITEXT, JORFTEXT) or a section (LEGISCTA); or a BOFiP id (BOI-…), with `article` for one paragraph.",
-  "type": "string"
-}
      • addedInput schema / properties / text_id
        Added value: +{
+  "description": "Légifrance id: an article (LEGIARTI, JORFARTI, KALIARTI), a text (LEGITEXT, JORFTEXT) or a section (LEGISCTA); or a BOFiP id (BOI-…), with `article` for one paragraph.",
+  "type": "string"
+}
      • changedInput schema / properties / url / description
        Previous value: -"A librejustice.fr article URL `/norm/{juridiction}/{code}/{article}`: take it from a search_norms hit or an inline citation link, or compose it: {juridiction} is the enacting state as ISO 3166-1 alpha-2 lowercase (\"fr\", \"be\"), \"eu\" for the Union, its treaties included, \"intl\" for a treaty signed outside it (the ECHR, a bilateral accord), {code} is the code slug (\"code-civil\", as in facets.legal_instrument), {article} the lowercase article key (\"l761-1\" for L. 761-1, \"1240\" for 1240). `/norm/{juridiction}/{code}` alone addresses the text itself, which is how a text with no articles (circulaire, publication decree) is read."New value: +"A librejustice.fr article URL `/norm/{jurisdiction}/{code}/{article}`: take it from a search_norms hit or an inline citation link, or compose it: {jurisdiction} is the enacting state as ISO 3166-1 alpha-2 lowercase (\"fr\", \"be\"), \"eu\" for the Union, its treaties included, \"intl\" for a treaty signed outside it (the ECHR, a bilateral accord), {code} is the code slug (\"code-civil\", as in facets.legal_instrument), {article} the lowercase article key (\"l761-1\" for L. 761-1, \"1240\" for 1240). `/norm/{jurisdiction}/{code}` alone addresses the text itself, which is how a text with no articles (circulaire, publication decree) is read."
      • removedOutput schema / properties / articleCount
        Removed value: -{
-  "type": "integer"
-}
      • addedOutput schema / properties / article_count
        Added value: +{
+  "type": "integer"
+}
      • removedOutput schema / properties / articles / items / properties / num
        Removed value: -{
-  "type": "string"
-}
      • addedOutput schema / properties / articles / items / properties / number
        Added value: +{
+  "type": "string"
+}
      • changedOutput schema / properties / articles / items / required
        Previous value: -[
-  "kind",
-  "num",
-  "url"
-]New value: +[
+  "kind",
+  "number",
+  "url"
+]
      • removedOutput schema / properties / commentaires
        Removed value: -{
-  "items": {
-    "additionalProperties": false,
-    "properties": {
-      "access": {
-        "anyOf": [
-          {
-            "enum": [
-              "libre",
-              "abonnes"
-            ],
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null
-      },
-      "author": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null
-      },
-      "date": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null,
-        "format": "date"
-      },
-      "issue": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null
-      },
-      "kind": {
-        "enum": [
-          "conclusions",
-          "note"
-        ],
-        "type": "string"
-      },
-      "pages": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null
-      },
-      "publisher": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null
-      },
-      "title": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null
-      },
-      "url": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null
-      },
-      "volume": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null
-      }
-    },
-    "required": [
-      "kind"
-    ],
-    "type": "object"
-  },
-  "type": "array"
-}
      • addedOutput schema / properties / commentaries
        Added value: +{
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "access": {
+        "anyOf": [
+          {
+            "enum": [
+              "libre",
+              "abonnes"
+            ],
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null
+      },
+      "author": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null
+      },
+      "body": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null
+      },
+      "date": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "format": "date"
+      },
+      "issue": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null
+      },
+      "kind": {
+        "enum": [
+          "summary",
+          "conclusions",
+          "note"
+        ],
+        "type": "string"
+      },
+      "pages": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null
+      },
+      "publisher": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null
+      },
+      "title": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null
+      },
+      "url": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null
+      },
+      "volume": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null
+      }
+    },
+    "required": [
+      "kind"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}
      • addedOutput schema / properties / date
        Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "format": "date"
+}
      • removedOutput schema / properties / dateDebut
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "format": "date"
-}
      • removedOutput schema / properties / dateFin
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "format": "date"
-}
      • removedOutput schema / properties / etat
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • addedOutput schema / properties / legislative_history
        Added value: +{
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "date": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "format": "date"
+      },
+      "href": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null
+      },
+      "label": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "label"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}
      • removedOutput schema / properties / modifiedBy
        Removed value: -{
-  "description": "Texts that created, modified or repealed this article.",
-  "items": {
-    "additionalProperties": false,
-    "properties": {
-      "date": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null,
-        "format": "date"
-      },
-      "href": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null
-      },
-      "label": {
-        "type": "string"
-      }
-    },
-    "required": [
-      "label"
-    ],
-    "type": "object"
-  },
-  "type": "array"
-}
      • addedOutput schema / properties / modified_by
        Added value: +{
+  "description": "Texts that created, modified or repealed this article.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "date": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "format": "date"
+      },
+      "href": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null
+      },
+      "label": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "label"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}
      • removedOutput schema / properties / nota
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • addedOutput schema / properties / note
        Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}
      • removedOutput schema / properties / num
        Removed value: -{
-  "type": "string"
-}
      • addedOutput schema / properties / number
        Added value: +{
+  "type": "string"
+}
      • removedOutput schema / properties / sourceUrl
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • addedOutput schema / properties / source_url
        Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}
      • addedOutput schema / properties / status
        Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}
      • removedOutput schema / properties / travauxParlementaires
        Removed value: -{
-  "items": {
-    "additionalProperties": false,
-    "properties": {
-      "date": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null,
-        "format": "date"
-      },
-      "href": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null
-      },
-      "label": {
-        "type": "string"
-      }
-    },
-    "required": [
-      "label"
-    ],
-    "type": "object"
-  },
-  "type": "array"
-}
      • addedOutput schema / properties / valid_from
        Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "format": "date"
+}
      • addedOutput schema / properties / valid_to
        Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "format": "date"
+}
      • removedOutput schema / properties / versions / items / properties / dateDebut
        Removed value: -{
-  "format": "date",
-  "type": "string"
-}
      • removedOutput schema / properties / versions / items / properties / dateFin
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "format": "date"
-}
      • removedOutput schema / properties / versions / items / properties / etat
        Removed value: -{
-  "type": "string"
-}
      • addedOutput schema / properties / versions / items / properties / status
        Added value: +{
+  "type": "string"
+}
      • addedOutput schema / properties / versions / items / properties / valid_from
        Added value: +{
+  "format": "date",
+  "type": "string"
+}
      • addedOutput schema / properties / versions / items / properties / valid_to
        Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "format": "date"
+}
      • changedOutput schema / properties / versions / items / required
        Previous value: -[
-  "etat",
-  "dateDebut"
-]New value: +[
+  "status",
+  "valid_from"
+]
    • Changedsearch_decisions12 fields changed
      • removedOutput schema / properties / hits / items / properties / aiSummary
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • addedOutput schema / properties / hits / items / properties / ai_summary
        Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}
      • removedOutput schema / properties / hits / items / properties / citedArticles
        Removed value: -{
-  "additionalProperties": {
-    "items": {
-      "type": "string"
-    },
-    "type": "array"
-  },
-  "type": "object"
-}
      • addedOutput schema / properties / hits / items / properties / cited_articles
        Added value: +{
+  "additionalProperties": {
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  },
+  "type": "object"
+}
      • addedOutput schema / properties / hits / items / properties / date
        Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "format": "date"
+}
      • removedOutput schema / properties / hits / items / properties / dateLecture
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "format": "date"
-}
      • removedOutput schema / properties / hits / items / properties / docketNumbers
        Removed value: -{
-  "anyOf": [
-    {
-      "items": {
-        "type": "string"
-      },
-      "type": "array"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • addedOutput schema / properties / hits / items / properties / docket_numbers
        Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}
      • removedOutput schema / properties / hits / items / properties / legalDomain
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • addedOutput schema / properties / hits / items / properties / legal_domain
        Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}
      • removedOutput schema / properties / hits / items / properties / officialUrl
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • addedOutput schema / properties / hits / items / properties / official_url
        Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}
    • Changedsearch_norms4 fields changed
      • addedInput schema / properties / as_of
        Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Consultation date (YYYY-MM-DD): searches the versions valid at that date (point-in-time, same semantics as get_norm). Omit to search the versions currently in force."
+}
      • removedInput schema / properties / date
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Consultation date (YYYY-MM-DD): searches the versions valid at that date (point-in-time, same semantics as get_norm). Omit to search the versions currently in force."
-}
      • removedOutput schema / properties / hits / items / properties / titlePath
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • addedOutput schema / properties / hits / items / properties / title_path
        Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}
  7. 2 tool updates
    • Changedget_norm1 field changed
      • changedInput schema / properties / textId / description
        Previous value: -"Légifrance id: an article (LEGIARTI, JORFARTI, KALIARTI), a text (LEGITEXT, JORFTEXT) or a section (LEGISCTA)."New value: +"Légifrance id: an article (LEGIARTI, JORFARTI, KALIARTI), a text (LEGITEXT, JORFTEXT) or a section (LEGISCTA); or a BOFiP id (BOI-…), with `article` for one paragraph."
    • Changedsearch_decisions3 fields changed
      • changedInput schema / properties / mode / description
        Previous value: -"'auto' is the right choice in almost all cases, it picks the regime from the query shape. auto: combines meaning and keyword matching on plain queries; switches to keyword-only when the query contains ET / OU / SAUF or quoted phrases. lexical: force keyword-only matching. Every term becomes required and nothing recovers a miss, so it fits a string you expect word for word (a consecrated formula, the direction of a holding, a party named in the text) and an empty answer is then an answer. reference: force the lookup by identity, on the docket number, the case name, or the court and the date. semantic: force the meaning+keyword hybrid even on quoted or operator queries (where auto would fall back to keyword-only)."New value: +"'auto' is the right choice in almost all cases. auto: automatically switches among 'semantic', 'lexical' and 'reference'. semantic: meaning + keyword hybrid, quoted phrases filter presence. lexical: keyword-only, every word required, quoted phrases exact, ET / AND / OU / OR / SAUF / NOT / PROCHE5 / NEAR5 / répar*. reference: lookup by identity, on the docket number, the ECLI, the case name, or the court and the date."
      • changedInput schema / properties / query / description
        Previous value: -"French query, the primary input. Two regimes, pick the right tool for the job: (a) Natural language or descriptive keywords for legal-issue searches; the engine handles synonyms and reformulations. Examples: « responsabilité hôpital infection nosocomiale » ; « étranger malade soins inaccessibles dans son pays d'origine » ; « licenciement discrimination syndicale charge de la preuve ». (b) Quoted exact phrases and ET / OU / SAUF operators for a named entity (company, municipality, person), a precise legal formula, or the direction of a holding: semantic matching ignores negations (« n'est pas X » ranks like « est X »), and only an exact phrase targets which way the court ruled. Examples: « \"Société Générale\" » ; « \"commune de Saint-Denis\" SAUF Réunion » ; « \"force majeure\" ET épidémie ». Using operators or quotes switches the engine to keyword-only matching for the whole query (no synonyms), so do not mix the two regimes."New value: +"The primary input, in the language of the decisions sought: a question or descriptive keywords on a legal issue (« licenciement discrimination syndicale charge de la preuve »), with quoted phrases for a name or a precise formula (« \"Société Générale\" responsabilité du banquier »); a boolean formula (« \"force majeure\" ET épidémie SAUF grippe »); or a reference (« 21PA01295 », « CE 13 juillet 2016 », « Czabaj »)."
      • changedInput schema / properties / sort / description
        Previous value: -"Result ordering. Use 'relevance' (default) unless the user wants chronological order."New value: +"Result ordering. Use 'relevance' (default) unless the user wants chronological order. A date order excludes mode 'semantic'."
  8. 1 tool update
    • Changedget_norm1 field changed
      • addedOutput schema / properties / modifiedBy / description
        Added value: +"Texts that created, modified or repealed this article."
  9. 1 tool update
    • Changedget_decision1 field changed
      • removedOutput schema / properties / appellateFate
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
  10. 1 tool update
    • Removedlist_my_activity
  11. 4 tool updates
    • Removedget_legal_text
    • Addedget_norm
    • Removedsearch_legal_texts
    • Addedsearch_norms
  12. 1 tool update
    • Changedget_legal_text1 field changed
      • changedInput schema / properties / url / description
        Previous value: -"A librejustice.fr article URL `/texte/{juridiction}/{code}/{article}`: take it from a search_legal_texts hit or an inline citation link, or compose it: {juridiction} is the enacting state as ISO 3166-1 alpha-2 lowercase (\"fr\", \"be\"), \"eu\" for the Union, its treaties included, \"intl\" for a treaty signed outside it (the ECHR, a bilateral accord), {code} is the code slug (\"code-civil\", as in facets.legal_instrument), {article} the lowercase article key (\"l761-1\" for L. 761-1, \"1240\" for 1240). `/texte/{juridiction}/{code}` alone addresses the text itself, which is how a text with no articles (circulaire, publication decree) is read."New value: +"A librejustice.fr article URL `/norm/{juridiction}/{code}/{article}`: take it from a search_legal_texts hit or an inline citation link, or compose it: {juridiction} is the enacting state as ISO 3166-1 alpha-2 lowercase (\"fr\", \"be\"), \"eu\" for the Union, its treaties included, \"intl\" for a treaty signed outside it (the ECHR, a bilateral accord), {code} is the code slug (\"code-civil\", as in facets.legal_instrument), {article} the lowercase article key (\"l761-1\" for L. 761-1, \"1240\" for 1240). `/norm/{juridiction}/{code}` alone addresses the text itself, which is how a text with no articles (circulaire, publication decree) is read."
  13. 1 tool update
    • Changedget_legal_text2 fields changed
      • changedInput schema / properties / textId / description
        Previous value: -"Légifrance article id (LEGIARTI…), resolved to the article it designates. LEGITEXT and CID are not accepted."New value: +"Légifrance id: an article (LEGIARTI, JORFARTI, KALIARTI), a text (LEGITEXT, JORFTEXT) or a section (LEGISCTA)."
      • addedOutput schema / properties / section
        Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "label": {
+      "type": "string"
+    },
+    "url": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "label",
+    "url"
+  ],
+  "type": "object"
+}
  14. 2 tool updates
    • Changedget_decision3 fields changed
      • addedOutput schema / properties / commentaires / items / properties / issue
        Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}
      • addedOutput schema / properties / commentaires / items / properties / pages
        Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}
      • addedOutput schema / properties / commentaires / items / properties / volume
        Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}
    • Changedget_legal_text3 fields changed
      • addedOutput schema / properties / commentaires / items / properties / issue
        Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}
      • addedOutput schema / properties / commentaires / items / properties / pages
        Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}
      • addedOutput schema / properties / commentaires / items / properties / volume
        Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}
  15. 1 tool update
    • Changedget_legal_text2 fields changed
      • addedOutput schema / properties / modifiedBy
        Added value: +{
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "date": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "format": "date"
+      },
+      "href": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null
+      },
+      "label": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "label"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}
      • addedOutput schema / properties / travauxParlementaires
        Added value: +{
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "date": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "format": "date"
+      },
+      "href": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null
+      },
+      "label": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "label"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}
  16. 2 tool updates
    • Changedget_decision4 fields changed
      • removedOutput schema / properties / commentaires / items / properties / body
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • changedOutput schema / properties / commentaires / items / properties / kind / enum
        Previous value: -[
-  "analyse",
-  "conclusions",
-  "note"
-]New value: +[
+  "conclusions",
+  "note"
+]
      • removedOutput schema / properties / commentaires / items / properties / renvois
        Removed value: -{
-  "items": {
-    "type": "string"
-  },
-  "type": "array"
-}
      • removedOutput schema / properties / commentaires / items / properties / rubriques
        Removed value: -{
-  "items": {
-    "type": "string"
-  },
-  "type": "array"
-}
    • Changedget_legal_text5 fields changed
      • changedInput schema / properties / url / description
        Previous value: -"A librejustice.fr article URL `/texte/{code}/{article}`: take it from a search_legal_texts hit or an inline citation link, or compose it: {code} is the code slug (\"code-civil\", as in facets.legal_instrument), {article} the lowercase article key (\"l761-1\" for L. 761-1, \"1240\" for 1240). `/texte/{code}` alone addresses the text itself, which is how a text with no articles (circulaire, publication decree) is read."New value: +"A librejustice.fr article URL `/texte/{juridiction}/{code}/{article}`: take it from a search_legal_texts hit or an inline citation link, or compose it: {juridiction} is the enacting state as ISO 3166-1 alpha-2 lowercase (\"fr\", \"be\"), \"eu\" for the Union, its treaties included, \"intl\" for a treaty signed outside it (the ECHR, a bilateral accord), {code} is the code slug (\"code-civil\", as in facets.legal_instrument), {article} the lowercase article key (\"l761-1\" for L. 761-1, \"1240\" for 1240). `/texte/{juridiction}/{code}` alone addresses the text itself, which is how a text with no articles (circulaire, publication decree) is read."
      • removedOutput schema / properties / commentaires / items / properties / body
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • changedOutput schema / properties / commentaires / items / properties / kind / enum
        Previous value: -[
-  "analyse",
-  "conclusions",
-  "note"
-]New value: +[
+  "conclusions",
+  "note"
+]
      • removedOutput schema / properties / commentaires / items / properties / renvois
        Removed value: -{
-  "items": {
-    "type": "string"
-  },
-  "type": "array"
-}
      • removedOutput schema / properties / commentaires / items / properties / rubriques
        Removed value: -{
-  "items": {
-    "type": "string"
-  },
-  "type": "array"
-}
  17. 1 tool update
    • Changedsearch_legal_texts1 field changed
      • addedOutput schema / properties / pinned
        Added value: +{
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "title": {
+        "type": "string"
+      },
+      "url": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "title",
+      "url"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}
  18. 1 tool update
    • Changedsearch_decisions1 field changed
      • changedInput schema / properties / seat / description
        Previous value: -"Restrict to one or more seats, as a dotted path from the court type down to the room: \"CA\" (a whole type), \"CA.PARIS\" and \"TJ.BORDEAUX\" (one court), \"CC.SOCIALE\", \"CA.PARIS.P5.C3\", \"TJ.LYON.SOCIALE\", \"TJ.PARIS.REFERES\", \"TA.MARSEILLE.C5\" (one room). A path matches itself and everything below it, so start at the type and go deeper. Types: TJ (tribunal judiciaire), CA (cour d'appel), CC (Cour de cassation), TCOM (tribunal des activités économiques), TA (tribunal administratif), CAA (cour administrative d'appel), CE (Conseil d'État), CNDA (asylum), CONSTIT (Conseil constitutionnel), TC (Tribunal des conflits), CNIL (sanctions), CEDH and CJUE (European courts). Take the paths from facets.seat."New value: +"Restrict to one or more seats, as a dotted path from the court type down to the room: \"CA\" (a whole type), \"CA.PARIS\" and \"TJ.BORDEAUX\" (one court), \"CC.C1_CIVILE\", \"CA.PARIS.P5.C3\", \"TJ.LYON.SOCIALE\", \"TJ.PARIS.REFERES\", \"TA.MARSEILLE.C5\" (one room). A path matches itself and everything below it, so start at the type and go deeper. Types: TJ (tribunal judiciaire), CA (cour d'appel), CC (Cour de cassation), TCOM (tribunal des activités économiques), TA (tribunal administratif), CAA (cour administrative d'appel), CE (Conseil d'État), CNDA (asylum), CONSTIT (Conseil constitutionnel), TC (Tribunal des conflits), CNIL (sanctions), CEDH and CJUE (European courts). Take the paths from facets.seat."
  19. 1 tool update
    • Changedsearch_decisions2 fields changed
      • changedInput schema / properties / mode / description
        Previous value: -"'auto' is the right choice in almost all cases, it picks the regime from the query shape. auto: combines meaning and keyword matching on plain queries; switches to keyword-only when the query contains ET / OU / SAUF or quoted phrases. lexical: force keyword-only matching. Every term becomes required and nothing recovers a miss, so it fits a string you expect word for word (a consecrated formula, the direction of a holding, a party named in the text) and an empty answer is then an answer. semantic: force the meaning+keyword hybrid even on quoted or operator queries (where auto would fall back to keyword-only)."New value: +"'auto' is the right choice in almost all cases, it picks the regime from the query shape. auto: combines meaning and keyword matching on plain queries; switches to keyword-only when the query contains ET / OU / SAUF or quoted phrases. lexical: force keyword-only matching. Every term becomes required and nothing recovers a miss, so it fits a string you expect word for word (a consecrated formula, the direction of a holding, a party named in the text) and an empty answer is then an answer. reference: force the lookup by identity, on the docket number, the case name, or the court and the date. semantic: force the meaning+keyword hybrid even on quoted or operator queries (where auto would fall back to keyword-only)."
      • changedInput schema / properties / mode / enum
        Previous value: -[
-  "auto",
-  "lexical",
-  "semantic"
-]New value: +[
+  "auto",
+  "lexical",
+  "semantic",
+  "reference"
+]

Related MCP Connectors

Related MCP Servers

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