LibreJustice
Server Details
Search French and European case law and French legal texts (codes, statutes, treaties).
- Status
- Healthy
- Uptime
- 99.7% over 37 days
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- librejustice/librejustice
- GitHub Stars
- 29
- Server Listing
- LibreJustice
TDQS
Scored across 5 tools
Tools are mostly distinct: two search tools target different resources (decisions vs. legal texts), and two fetch tools retrieve specific entities by URL. However, search_decisions and search_legal_texts both use 'search' verbs and could be confused without careful reading, though their descriptions clarify the object type.
Naming follows a consistent verb_noun pattern: get_decision, get_legal_text, search_decisions, search_legal_texts, and list_my_activity all use verb_noun. The pattern is clear, though 'list_my_activity' is slightly verbose and the object is a collection rather than a single resource, but it still fits the pattern.
With 5 tools covering search, retrieval, and user activity, the count is well-scoped for a legal research MCP server. Each tool has a distinct role, and none feel superfluous; the server appears focused and efficient.
The surface covers core legal research workflows: searching for decisions and texts, fetching full content, and user activity. However, there are gaps: no tool for listing or browsing decisions by jurisdiction or court without a query, and no direct way to retrieve a decision by ID (only by URL from search). Also, the user activity tool is a minor feature, not core to legal research, but the missing browsing capability is a notable gap.
Available Tools
5 toolsget_decisionGet DecisionARead-onlyIdempotentInspect
Fetch the full text and metadata of a decision by its url. The text carries inline markdown links to cited articles (/texte/, open with get_legal_text) 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. appellateFate states in one line what became of THIS decision on review (INFIRMATION = reversed, it no longer stands; CONFIRMATION = upheld): read it before citing the decision as authority. caseChronology lists the prior AND subsequent decisions of the same case (appeal, pourvoi, renvoi). An absent fate or chronology never proves no recourse exists, only that none is linked in the corpus. commentaires links out to the rapporteur public's conclusions and the court's related documents: context, never the ruling, so quote the decision text and not a commentaire.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | A librejustice.fr decision URL, from a search_decisions hit or an inline citation link; search_decisions first if you have neither. |
Output Schema
| Name | Required | Description |
|---|---|---|
| url | Yes | |
| seat | No | |
| text | Yes | |
| title | Yes | |
| office | No | |
| solution | No | |
| procedure | No | |
| dateLecture | No | |
| legalDomain | No | |
| officialUrl | No | |
| publication | No | |
| commentaires | No | |
| appellateFate | No | |
| docketNumbers | No | |
| caseChronology | No | |
| jurisdictionCode | No | |
| jurisdictionType | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations only provide safety signals (readOnly, idempotent, non-destructive), while the description discloses rich behavioral details: inline markdown link formats, multi-article citation handling, the meaning of appellateFate, the scope of caseChronology, and the caveat that commentaires are context rather than ruling. Nothing in the description contradicts the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is dense but every sentence earns its place: it covers purpose, linking behavior, field semantics, and usage caveats without repetition. Important warnings are front-loaded after the core fetch statement, and the structure makes the legal interpretation guidance easy to locate.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the output schema exists and the tool has only one required parameter, the description is complete for safe invocation. It explains not only what the tool returns but also how to interpret ambiguous or absent fields, which is critical for a legal citation tool. No essential call-time guidance is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already fully describes the `url` parameter, so the baseline is 3. The description adds value by specifying the URL must be a librejustice.fr decision URL, and clarifies the expected source: a search_decisions hit or an inline citation link, with search_decisions as the fallback. This goes beyond the schema but does not add exhaustive format detail.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
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 the full text and metadata of a decision by its `url`.' It also differentiates itself from siblings by explaining how cited decisions open with get_decision and cited articles open with get_legal_text, so the agent can clearly distinguish roles.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly tells the agent when to use this tool versus alternatives: use it for decision URLs from search_decisions hits or inline citation links, and use search_decisions first if neither is available. It also includes warnings about not treating absent fate or chronology as proof that no recourse exists.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_legal_textGet Legal TextARead-onlyIdempotentInspect
Fetch a legal text, or one of its articles, as it stood on a given date. Returns the version in force at date (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 (/texte/, open with get_legal_text; when served at a date, the links point to the same date). commentaires links out to commentary anchored on the article. num 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. Covers French codes and statutes, plus curated foreign codes and treaties.
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | 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. | |
| code | No | Code slug, when you hold the code and the article apart rather than as a url ("code-civil"). Alone, addresses the text itself. | |
| date | No | Consultation date (YYYY-MM-DD): returns the version in force at that date. Omit for the version currently in force. | |
| textId | No | Légifrance id: an article (LEGIARTI, JORFARTI, KALIARTI), a text (LEGITEXT, JORFTEXT) or a section (LEGISCTA). | |
| article | No | Lowercase article key, alongside `code` ("l761-1" for L. 761-1, "1240" for 1240). |
Output Schema
| Name | Required | Description |
|---|---|---|
| num | No | |
| url | Yes | |
| code | Yes | |
| etat | No | |
| nota | No | |
| text | No | |
| title | Yes | |
| dateFin | No | |
| omitted | No | |
| section | No | |
| articles | No | |
| versions | Yes | |
| dateDebut | No | |
| sourceUrl | No | |
| modifiedBy | No | |
| articleCount | No | |
| commentaires | No | |
| travauxParlementaires | No |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With readOnlyHint, idempotentHint, destructiveHint, and openWorldHint all already provided by annotations, the description adds substantial behavioral context: date-scoped versioning, inline markdown cross-reference links that follow the consultation date, commentary links, and the semantic distinction between whole-text and article URLs. This goes well beyond the annotation safety profile.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is long but dense and front-loaded with the core fetch purpose before diving into URL mechanics and link behavior. Every sentence carries operational detail needed for correct invocation, so the length is justified despite the paragraph-style structure.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has an output schema and annotations, the description sufficiently covers all five parameters, return contents, versioning, cross-references, and the special cases of texts without articles and article-section URLs. An agent has enough guidance to invoke the tool correctly in diverse scenarios.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Although schema coverage is 100%, the description adds significant semantic value beyond the schema: it explains URL composition with juridiction/code/article examples, the distinction between /texte/{juridiction}/{code} and /texte/{juridiction}/{code}/{article}, and the Légifrance ID families (LEGIARTI, JORFTEXT, etc.). This materially helps an agent construct valid inputs.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
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.' This clearly distinguishes the tool from siblings like search_legal_texts, which locates texts, and get_decision, which retrieves decisions. The scope is further clarified by coverage of French codes, statutes, and curated foreign codes/treaties.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the workflow by saying a URL can be 'take[n] from a search_legal_texts hit or an inline citation link,' and explains the omit-date behavior for current versions. It does not explicitly state when not to use the tool or name alternatives, but the read/fetch role versus the search role is reasonably clear from context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
list_my_activityList My ActivityARead-onlyIdempotentInspect
List the authenticated user's own activity, most recent first. kind selects which tab: 'searches' (past queries with their structured filters and source), 'bookmarks' or 'readingHistory' (decisions, each with title, a summary and the url to chain into get_decision), or 'all' to get the three at once. Only the requested tab(s) are populated. In readingHistory, lastSource == 'web' means the user opened the decision manually at least once (a genuine read); 'mcp' means it was only ever opened through this connector. Requires a connected account.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | No | Which tab to list: 'searches', 'bookmarks', 'readingHistory', or 'all' (default) for the three at once. | all |
| limit | No | Maximum number of entries per tab (1–100, default 50). |
Output Schema
| Name | Required | Description |
|---|---|---|
| searches | No | |
| bookmarks | No | |
| readingHistory | No |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the operation read-only, idempotent, and non-destructive, and the description adds genuinely new behavioral context: most-recent-first ordering, only requested tabs being populated, the meaning of lastSource 'web' vs 'mcp', and the requirement of a connected account. No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The first sentence is a front-loaded summary, and the subsequent sentences expand the kind parameter with no filler. It is dense but every clause carries decision-relevant information about behavior, output interpretation, or prerequisites.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With an output schema present, return-value details do not need repeating. The description covers authentication, ordering, tab population, chaining to get_decision, and per-kind semantics, leaving nothing an agent needs to select and invoke the tool correctly missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already documents both parameters with defaults and ranges, so the baseline is 3. The description goes beyond the schema by explaining what each kind returns, noting that 'all' returns the three tabs at once, and defining the readingHistory lastSource semantics relevant to returned data.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
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—'List the authenticated user's own activity'—and immediately states ordering. It enumerates the three tab kinds and the 'all' aggregate, making the tool's scope clear and distinguishable from the sibling decision-search and retrieval tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It gives strong when-to-use context: for viewing the user's recent searches, bookmarks, or reading history, and explicitly says URLs from readingHistory chain into get_decision. It does not explicitly name sibling alternatives or exclusion cases, but the tab semantics make the intended use unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_decisionsSearch DecisionsARead-onlyIdempotentInspect
Search decisions by meaning and keywords combined. Returns a shortlist: title, url, an overview (aiSummary: AI-written summary of what the decision is about, a machine paraphrase never quotable as the court's words; 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, legalDomain or solution passes back verbatim into the matching filter.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | '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). | auto |
| seat | No | 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. | |
| sort | No | Result ordering. Use 'relevance' (default) unless the user wants chronological order. | relevance |
| limit | No | Maximum number of results (default 10). | |
| query | Yes | 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. | |
| office | No | Filter by specialised judge/office (JLD, JAF, JCP, JEX, juge des enfants, premier président, magistrat désigné). Absent value = ordinary bench. | |
| date_to | No | Latest decision date, inclusive (YYYY-MM-DD). | |
| solution | No | Filter 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_rerank | No | When 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_from | No | Earliest decision date, inclusive (YYYY-MM-DD). | |
| procedure | No | Filter by procedural track (référés, QPC, EU referral, révision, tierce opposition…). Absent value = ordinary contentious procedure. | |
| publication | No | Filter 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_domain | No | Filter 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_article | No | Restrict 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_instrument | No | Restrict 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
| Name | Required | Description |
|---|---|---|
| hits | Yes | |
| query | Yes | |
| total | Yes | |
| facets | No | |
| pinned | No |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations cover safety (readOnly, idempotent, non-destructive), so the description carries a lower burden, but it still adds significant behavioral detail: aiSummary is a machine paraphrase never quotable as the court's words, snippet is verbatim; filters are OR'd within a filter and AND'd across filters; facets expose counts and keys to reuse verbatim; and mode behavior is disclosed (semantic matching ignores negations, quoted phrases switch to keyword-only). No contradiction with annotations exists.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is dense but well-structured: it opens with the core action, then the return payload, then usage guidance, then filter/facet behavior. Each sentence adds distinct information, with no filler or tautology. It is long, but given 15 parameters and the complexity of the query regimes, the length is justified.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the rich input schema, output schema, and safety annotations, the description covers everything an agent needs for correct invocation: query-regime rules, mode selection, filter semantics, facet reuse, reranker tradeoffs, and routing to get_decision for full text. Nothing essential is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description adds meaningful cross-parameter semantics beyond the individual schema entries: the OR/AND filter composition rule, the instruction to reuse facet keys verbatim, and the symmetry between hit metadata fields and matching filters. This provides extra value without needing to restate every parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description leads with a specific verb and resource: 'Search decisions by meaning and keywords combined.' It explicitly names the return shortlist (title, url, overview, metadata) and distinguishes itself from the sibling get_decision, which 'reads the full text.' This leaves no ambiguity about what the tool does or how it differs from its siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives clear usage context: keep the query for the legal issue, put constraints in structured filters, and use get_decision for full text. It also provides strong mode-selection guidance ('auto' is right in almost all cases) and explains when to force lexical or reference modes. It does not explicitly mention search_legal_texts as an alternative, but the decision-focused scope and schema make the intended use clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_legal_textsSearch Legal TextsARead-onlyIdempotentInspect
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. 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_legal_text with its url, plus date when the dispute is governed by an earlier version.
| Name | Required | Description | Default |
|---|---|---|---|
| code | No | Restrict to one code/text by its URL slug ("code-civil", as in facets.code) or exact name. Omit to search the whole navigable referential. | |
| date | No | Consultation date (YYYY-MM-DD): searches the versions valid at that date (point-in-time, same semantics as get_legal_text). Omit to search the versions currently in force. | |
| limit | No | Maximum number of results (default 10). | |
| query | Yes | French query over legal articles. Matches article titles (boosted) and bodies; alias expansion handles acronyms and usual names. | |
| jurisdiction | No | 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. |
Output Schema
| Name | Required | Description |
|---|---|---|
| hits | Yes | |
| query | Yes | |
| total | Yes | |
| facets | Yes | |
| pinned | No |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnlyHint/idempotentHint annotations, the description discloses the return shape (shortlist, highlighted snippets, exact total), the facets block semantics, and the suggested chaining behavior. It also clarifies the point-in-time date nuance for earlier versions, adding meaningful behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The text is dense but every clause earns its place: purpose, query formulation, facets mechanism, and chaining guidance all appear without fluff. The main purpose is front-loaded before the technical details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a search tool with a rich output schema and safe annotations, the description covers what an agent needs to call it correctly: query scope, filter usage, facet reuse, and the follow-up call to get_legal_text. No critical behavior is missing for this complexity level.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3, but the description adds practical parameter semantics: how to split content between the query and the code filter, that code accepts slugs or exact names, and when to pass date. This goes beyond the schema without restating it verbatim.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific action and resource: 'Find legal articles' by subject, wording, or article number without a code name. It is clear, but it does not explicitly distinguish this from the sibling search_decisions tool, so the differentiation is left mostly to the tool names.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It gives concrete usage instructions: query in French, keep subject in the query, put the code in the code filter, and chain hits into get_legal_text with url and optionally date. It does not explicitly state when not to use it or name alternatives such as search_decisions for decisions, so it stops short of full exclusion guidance.
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 tool update
- Changed
get_legal_text2 fields changed- changed
Input schema / properties / textId / descriptionPrevious 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)." - added
Output schema / properties / sectionAdded value: +{ + "additionalProperties": false, + "properties": { + "label": { + "type": "string" + }, + "url": { + "type": "string" + } + }, + "required": [ + "label", + "url" + ], + "type": "object" +}
2 tool updates
- Changed
get_decision3 fields changed- added
Output schema / properties / commentaires / items / properties / issueAdded value: +{ + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null +} - added
Output schema / properties / commentaires / items / properties / pagesAdded value: +{ + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null +} - added
Output schema / properties / commentaires / items / properties / volumeAdded value: +{ + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null +}
- Changed
get_legal_text3 fields changed- added
Output schema / properties / commentaires / items / properties / issueAdded value: +{ + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null +} - added
Output schema / properties / commentaires / items / properties / pagesAdded value: +{ + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null +} - added
Output schema / properties / commentaires / items / properties / volumeAdded value: +{ + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null +}
1 tool update
- Changed
get_legal_text2 fields changed- added
Output schema / properties / modifiedByAdded 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" +} - added
Output schema / properties / travauxParlementairesAdded 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" +}
2 tool updates
- Changed
get_decision4 fields changed- removed
Output schema / properties / commentaires / items / properties / bodyRemoved value: -{ - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null -} - changed
Output schema / properties / commentaires / items / properties / kind / enumPrevious value: -[ - "analyse", - "conclusions", - "note" -]New value: +[ + "conclusions", + "note" +] - removed
Output schema / properties / commentaires / items / properties / renvoisRemoved value: -{ - "items": { - "type": "string" - }, - "type": "array" -} - removed
Output schema / properties / commentaires / items / properties / rubriquesRemoved value: -{ - "items": { - "type": "string" - }, - "type": "array" -}
- Changed
get_legal_text5 fields changed- changed
Input schema / properties / url / descriptionPrevious 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." - removed
Output schema / properties / commentaires / items / properties / bodyRemoved value: -{ - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null -} - changed
Output schema / properties / commentaires / items / properties / kind / enumPrevious value: -[ - "analyse", - "conclusions", - "note" -]New value: +[ + "conclusions", + "note" +] - removed
Output schema / properties / commentaires / items / properties / renvoisRemoved value: -{ - "items": { - "type": "string" - }, - "type": "array" -} - removed
Output schema / properties / commentaires / items / properties / rubriquesRemoved value: -{ - "items": { - "type": "string" - }, - "type": "array" -}
1 tool update
- Changed
search_legal_texts1 field changed- added
Output schema / properties / pinnedAdded value: +{ + "items": { + "additionalProperties": false, + "properties": { + "title": { + "type": "string" + }, + "url": { + "type": "string" + } + }, + "required": [ + "title", + "url" + ], + "type": "object" + }, + "type": "array" +}
1 tool update
- Changed
search_decisions1 field changed- changed
Input schema / properties / seat / descriptionPrevious 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."
1 tool update
- Changed
search_decisions2 fields changed- changed
Input schema / properties / mode / descriptionPrevious 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)." - changed
Input schema / properties / mode / enumPrevious value: -[ - "auto", - "lexical", - "semantic" -]New value: +[ + "auto", + "lexical", + "semantic", + "reference" +]
1 tool update
- Changed
search_decisions8 fields changed- removed
Input schema / properties / jurisdiction_codeRemoved value: -{ - "anyOf": [ - { - "items": { - "maxLength": 40, - "type": "string" - }, - "maxItems": 10, - "type": "array" - }, - { - "type": "null" - } - ], - "default": null, - "description": "Restrict to one or more precise court units by referential code. Code shapes: \"cc\" (Cour de cassation), \"ce\" (Conseil d'État), \"cnda\", \"cedh\", \"cjue\"; \"ca_<city>\", \"caa_<city>\", \"ta_<city>\", \"tj_<city>\", \"tcom_<city>\" (e.g. \"ca_paris\", \"ta_marseille\", \"tj_paris\", \"tcom_lyon\"). When unsure, guess with the city name in the code: the error names the nearest valid ones. Each code is a court; a room inside it is reached with seat, which also expresses this filter as a path." -} - removed
Input schema / properties / jurisdiction_typeRemoved value: -{ - "anyOf": [ - { - "items": { - "enum": [ - "TA", - "CAA", - "CE", - "CONSTIT", - "TC", - "CC", - "CA", - "TJ", - "TCOM", - "CEDH", - "CJUE", - "CNDA", - "CNIL" - ], - "type": "string" - }, - "type": "array" - }, - { - "type": "null" - } - ], - "default": null, - "description": "Restrict to one or more court categories: 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)." -} - changed
Input schema / properties / seat / descriptionPrevious value: -"Restrict to one or more seats, as a dotted path from the court type down to the room: \"CC\", \"CC.SOCIALE\", \"CA.PARIS\", \"CA.PARIS.P5.C3\". A path matches itself and everything below it, so this one filter also covers what jurisdiction_type and jurisdiction_code express. 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.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." - removed
Output schema / properties / filterRewrittenRemoved value: -{ - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null -} - added
Output schema / properties / hits / items / properties / citedArticlesAdded value: +{ + "additionalProperties": { + "items": { + "type": "string" + }, + "type": "array" + }, + "type": "object" +} - removed
Output schema / properties / hits / items / properties / jurisdictionCodeRemoved value: -{ - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null -} - removed
Output schema / properties / hits / items / properties / jurisdictionTypeRemoved value: -{ - "type": "string" -} - changed
Output schema / properties / hits / items / requiredPrevious value: -[ - "title", - "url", - "chars", - "jurisdictionType" -]New value: +[ + "title", + "url", + "chars" +]
5 tool updates
- Changed
get_decision17 fields changed- removed
Output schema / descriptionRemoved value: -"Metadata fields carry search_decisions filter tokens: each field matches the filter of the same name (jurisdictionType → jurisdiction_type, legalDomain → legal_domain…) and its value passes back verbatim to filter." - removed
Output schema / properties / appellateFate / descriptionRemoved value: -"Fate of THIS decision before the court that reviewed it, precomputed from caseChronology: 'INFIRMATION, Cour d'appel de Paris, 1 juillet 2025 (url)'. INFIRMATION = this decision was reversed and no longer stands; CONFIRMATION = upheld. Absent = no recourse known to the corpus, which never proves the decision is final." - removed
Output schema / properties / caseChronology / descriptionRemoved value: -"Prior and subsequent decisions of the same case (appeal, pourvoi, renvoi), most recent first, current decision included. The fate of a judgment reads in the solution of the decision that reviewed it (INFIRMATION = reversed, CONFIRMATION = upheld). Absent chronology never proves no recourse exists." - removed
Output schema / properties / caseChronology / items / properties / linkToNext / descriptionRemoved value: -"Link nature to the step below (the attacked decision): APPEL_DE | POURVOI_CONTRE | RENVOI_APRES_CASSATION." - removed
Output schema / properties / caseChronology / items / properties / url / descriptionRemoved value: -"Absent when the corpus does not hold that step: it is named by the decision that attacks it, and cannot be opened." - removed
Output schema / properties / chamberRemoved value: -{ - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null, - "description": "Chamber that heard the case, as \"<court>|<chamber>\", reusable verbatim as the chamber filter." -} - removed
Output schema / properties / commentaires / descriptionRemoved value: -"Institutional commentary anchored on this document: court-written analyses served inline (`body`), plus outbound links (`url`) to the rapporteur public's conclusions and to related institutional documents (reports, opinions, press releases). Context, never the ruling itself. Quote the decision text, not a commentaire, as the court's words." - changed
Output schema / properties / commentaires / items / properties / access / anyOfPrevious value: -[ - { - "type": "string" - }, - { - "type": "null" - } -]New value: +[ + { + "enum": [ + "libre", + "abonnes" + ], + "type": "string" + }, + { + "type": "null" + } +] - removed
Output schema / properties / commentaires / items / properties / access / descriptionRemoved value: -"libre | abonnes" - removed
Output schema / properties / commentaires / items / properties / kind / descriptionRemoved value: -"analyse = official court-written abstract, full content in `body`. conclusions = the rapporteur public's conclusions, `url` only (copyright-protected, existence + official link). note = linked institutional document (report, avocat général's opinion, press release, doctrine note), `url` + `title` + `publisher`." - added
Output schema / properties / commentaires / items / properties / kind / enumAdded value: +[ + "analyse", + "conclusions", + "note" +] - removed
Output schema / properties / commentaires / items / properties / renvois / descriptionRemoved value: -"Doctrinal cross-references of the analyse (« Cf. CE, … »)." - removed
Output schema / properties / commentaires / items / properties / rubriques / descriptionRemoved value: -"Official classification headings (analyse)." - removed
Output schema / properties / commentaires / items / properties / url / descriptionRemoved value: -"External link, to hand to the user, not openable by an MCP tool." - removed
Output schema / properties / officialUrl / descriptionRemoved value: -"The decision on its official publisher: legifrance.gouv.fr, courdecassation.fr, opendata.justice-administrative.fr, conseil-constitutionnel.fr, hudoc, eur-lex. Cite this when the deliverable requires the authoritative source; `url` is the LibreJustice page. Absent when the publisher exposes no per-decision permalink." - removed
Output schema / properties / publication / descriptionRemoved value: -"Publication values carried, reusable verbatim as the publication filter." - added
Output schema / properties / seatAdded value: +{ + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null +}
- Changed
get_legal_text14 fields changed- removed
Output schema / properties / articleCount / descriptionRemoved value: -"Number of articles the text carries. Present only on the root of a text with articles." - removed
Output schema / properties / articles / descriptionRemoved value: -"Contents of a text root or of one of its divisions, in reading order. Each `url` goes back to get_legal_text; a `section` entry returns all its articles at once, which is the cheapest way to read a chapter. `text` is joined only within the inline reading budget." - removed
Output schema / properties / articles / items / properties / num / descriptionRemoved value: -"Article number, or the division title when `kind` is `section`." - removed
Output schema / properties / commentaires / descriptionRemoved value: -"Institutional commentary anchored on this document: court-written analyses served inline (`body`), plus outbound links (`url`) to the rapporteur public's conclusions and to related institutional documents (reports, opinions, press releases). Context, never the ruling itself. Quote the decision text, not a commentaire, as the court's words." - changed
Output schema / properties / commentaires / items / properties / access / anyOfPrevious value: -[ - { - "type": "string" - }, - { - "type": "null" - } -]New value: +[ + { + "enum": [ + "libre", + "abonnes" + ], + "type": "string" + }, + { + "type": "null" + } +] - removed
Output schema / properties / commentaires / items / properties / access / descriptionRemoved value: -"libre | abonnes" - removed
Output schema / properties / commentaires / items / properties / kind / descriptionRemoved value: -"analyse = official court-written abstract, full content in `body`. conclusions = the rapporteur public's conclusions, `url` only (copyright-protected, existence + official link). note = linked institutional document (report, avocat général's opinion, press release, doctrine note), `url` + `title` + `publisher`." - added
Output schema / properties / commentaires / items / properties / kind / enumAdded value: +[ + "analyse", + "conclusions", + "note" +] - removed
Output schema / properties / commentaires / items / properties / renvois / descriptionRemoved value: -"Doctrinal cross-references of the analyse (« Cf. CE, … »)." - removed
Output schema / properties / commentaires / items / properties / rubriques / descriptionRemoved value: -"Official classification headings (analyse)." - removed
Output schema / properties / commentaires / items / properties / url / descriptionRemoved value: -"External link, to hand to the user, not openable by an MCP tool." - removed
Output schema / properties / num / descriptionRemoved value: -"Article key. Absent when the url addressed the root of a text: with no articles the payload is the whole text, `text` carrying its body; with articles it is the table of contents, `articles` carrying it." - removed
Output schema / properties / omitted / descriptionRemoved value: -"Articles served without their body because the text or division exceeds the inline reading budget: their `url` fetches them." - removed
Output schema / properties / text / descriptionRemoved value: -"Full text; cross-references to other articles render as inline markdown links (/texte/ urls, open with get_legal_text)."
- Changed
list_my_activity3 fields changed- removed
Output schema / descriptionRemoved value: -"One flat payload for every tab: a slice is filled only when it was asked for, by a targeted `kind` or by `all`." - changed
Output schema / properties / bookmarks / anyOfPrevious value: -[ - { - "additionalProperties": false, - "properties": { - "bookmarks": { - "items": { - "additionalProperties": false, - "description": "Decision reference for bookmarks and reading history: enough to cite it or to chain into get_decision with its `url`, without the full text.", - "properties": { - "bookmarkedAt": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null, - "format": "date-time" - }, - "dateLecture": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null, - "format": "date" - }, - "lastSource": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null - }, - "lastViewedAt": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null, - "format": "date-time" - }, - "solution": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null - }, - "summary": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null - }, - "title": { - "type": "string" - }, - "url": { - "type": "string" - }, - "viewCount": { - "anyOf": [ - { - "type": "integer" - }, - { - "type": "null" - } - ], - "default": null - } - }, - "required": [ - "title", - "url" - ], - "type": "object" - }, - "type": "array" - }, - "total": { - "type": "integer" - } - }, - "required": [ - "total", - "bookmarks" - ], - "type": "object" - }, - { - "type": "null" - } -]New value: +[ + { + "additionalProperties": false, + "properties": { + "bookmarks": { + "items": { + "additionalProperties": false, + "properties": { + "bookmarkedAt": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "format": "date-time" + }, + "dateLecture": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "format": "date" + }, + "lastSource": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null + }, + "lastViewedAt": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "format": "date-time" + }, + "solution": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null + }, + "summary": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null + }, + "title": { + "type": "string" + }, + "url": { + "type": "string" + }, + "viewCount": { + "anyOf": [ + { + "type": "integer" + }, + { + "type": "null" + } + ], + "default": null + } + }, + "required": [ + "title", + "url" + ], + "type": "object" + }, + "type": "array" + }, + "total": { + "type": "integer" + } + }, + "required": [ + "total", + "bookmarks" + ], + "type": "object" + }, + { + "type": "null" + } +] - changed
Output schema / properties / readingHistory / anyOfPrevious value: -[ - { - "additionalProperties": false, - "properties": { - "decisions": { - "items": { - "additionalProperties": false, - "description": "Decision reference for bookmarks and reading history: enough to cite it or to chain into get_decision with its `url`, without the full text.", - "properties": { - "bookmarkedAt": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null, - "format": "date-time" - }, - "dateLecture": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null, - "format": "date" - }, - "lastSource": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null - }, - "lastViewedAt": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null, - "format": "date-time" - }, - "solution": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null - }, - "summary": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null - }, - "title": { - "type": "string" - }, - "url": { - "type": "string" - }, - "viewCount": { - "anyOf": [ - { - "type": "integer" - }, - { - "type": "null" - } - ], - "default": null - } - }, - "required": [ - "title", - "url" - ], - "type": "object" - }, - "type": "array" - }, - "total": { - "type": "integer" - } - }, - "required": [ - "total", - "decisions" - ], - "type": "object" - }, - { - "type": "null" - } -]New value: +[ + { + "additionalProperties": false, + "properties": { + "decisions": { + "items": { + "additionalProperties": false, + "properties": { + "bookmarkedAt": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "format": "date-time" + }, + "dateLecture": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "format": "date" + }, + "lastSource": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null + }, + "lastViewedAt": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "format": "date-time" + }, + "solution": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null + }, + "summary": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null + }, + "title": { + "type": "string" + }, + "url": { + "type": "string" + }, + "viewCount": { + "anyOf": [ + { + "type": "integer" + }, + { + "type": "null" + } + ], + "default": null + } + }, + "required": [ + "title", + "url" + ], + "type": "object" + }, + "type": "array" + }, + "total": { + "type": "integer" + } + }, + "required": [ + "total", + "decisions" + ], + "type": "object" + }, + { + "type": "null" + } +]
- Changed
search_decisions18 fields changed- removed
Input schema / properties / chamberRemoved value: -{ - "anyOf": [ - { - "items": { - "maxLength": 60, - "type": "string" - }, - "maxItems": 10, - "type": "array" - }, - { - "type": "null" - } - ], - "default": null, - "description": "Restrict to one or more chambers, as a composite key \"<court>|<chamber>\" where <court> is a jurisdiction_code (e.g. \"ca_paris|C3\", \"cc|C2\", \"cc|SOCIALE\"). The court prefix is required: a chamber key names a different chamber in each court, \"C1\" alone existing in about 200 of them. The chamber part is slots joined by a dot, in the order they render: tag P (pôle), SC (section holding chambers), C (chambre), S (section), L (lettered section), Q (sous-sections réunies) or R (chambres réunies), then its number or letter. So \"P5.C6\" is pôle 5, 6e chambre, \"C5.LA\" section A of the 5th, \"CD\" chambre D, \"R3-8\" chambres 3/8 réunies (numbers in a reunited list always ascending). A chamber that no coordinate positions is keyed by what it judges instead (\"cc|SOCIALE\", \"cc|CRIMINELLE\"). facets.chamber lists the pairs present, and only once jurisdiction_code narrows the search to one or more courts." -} - changed
Input schema / properties / jurisdiction_code / descriptionPrevious value: -"Restrict to one or more precise court units by referential code. Code shapes: \"cc\" (Cour de cassation), \"ce\" (Conseil d'État), \"cnda\", \"cedh\", \"cjue\"; \"ca_<city>\", \"caa_<city>\", \"ta_<city>\", \"tj_<city>\", \"tcom_<city>\" (e.g. \"ca_paris\", \"ta_marseille\", \"tj_paris\", \"tcom_lyon\"). When unsure, guess with the city name in the code: the error names the nearest valid ones. Each code is a court; the chamber inside it is a separate filter (see chamber); use jurisdiction_type for the broad category."New value: +"Restrict to one or more precise court units by referential code. Code shapes: \"cc\" (Cour de cassation), \"ce\" (Conseil d'État), \"cnda\", \"cedh\", \"cjue\"; \"ca_<city>\", \"caa_<city>\", \"ta_<city>\", \"tj_<city>\", \"tcom_<city>\" (e.g. \"ca_paris\", \"ta_marseille\", \"tj_paris\", \"tcom_lyon\"). When unsure, guess with the city name in the code: the error names the nearest valid ones. Each code is a court; a room inside it is reached with seat, which also expresses this filter as a path." - changed
Input schema / properties / mode / descriptionPrevious 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. Never for a docket number or a decision name, which auto resolves by exact key. semantic: force the meaning+keyword hybrid even on quoted or operator queries (where auto would fall back to keyword-only). Naming a mode, like adding ET / OU / SAUF, also keeps a docket number inside an ordinary query instead of resolving it alone."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. semantic: force the meaning+keyword hybrid even on quoted or operator queries (where auto would fall back to keyword-only)." - changed
Input schema / properties / publication / anyOfPrevious value: -[ - { - "items": { - "enum": [ - "PUBLIE_BULLETIN", - "PUBLIE_RAPPORT", - "LETTRE_CHAMBRE", - "COMMUNIQUE", - "INEDIT_BULLETIN", - "PUBLIE_LEBON", - "MENTIONNE_LEBON", - "INEDIT_LEBON" - ], - "type": "string" - }, - "type": "array" - }, - { - "type": "null" - } -]New value: +[ + { + "items": { + "enum": [ + "PUBLIE_RAPPORT", + "PUBLIE_BULLETIN", + "LETTRE_CHAMBRE", + "COMMUNIQUE", + "INEDIT_BULLETIN", + "PUBLIE_LEBON", + "MENTIONNE_LEBON", + "INEDIT_LEBON" + ], + "type": "string" + }, + "type": "array" + }, + { + "type": "null" + } +] - changed
Input schema / properties / publication / descriptionPrevious value: -"Filter 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_BULLETIN, PUBLIE_RAPPORT (annual report, the strongest signal), LETTRE_CHAMBRE, COMMUNIQUE, INEDIT_BULLETIN. Administrative order: PUBLIE_LEBON, MENTIONNE_LEBON, INEDIT_LEBON. Lower courts carry no publication statement and match no value."New value: +"Filter 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." - changed
Input schema / properties / query / descriptionPrevious 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: a quoted phrase followed by free words requires every one of them in the same decision. (c) A docket number or a decision name takes neither quotes nor operators: « 21PA01295 », « n° 19-20.682 », « arrêt Danthony » are matched by an exact key, whatever the spelling, and quoting them only costs the recovery that catches a miss."New 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." - added
Input schema / properties / seatAdded value: +{ + "anyOf": [ + { + "items": { + "maxLength": 60, + "type": "string" + }, + "maxItems": 10, + "type": "array" + }, + { + "type": "null" + } + ], + "default": null, + "description": "Restrict to one or more seats, as a dotted path from the court type down to the room: \"CC\", \"CC.SOCIALE\", \"CA.PARIS\", \"CA.PARIS.P5.C3\". A path matches itself and everything below it, so this one filter also covers what jurisdiction_type and jurisdiction_code express. Take the paths from facets.seat." +} - removed
Output schema / properties / facets / descriptionRemoved value: -"Per filter name, a map of filter value to decision count under the current query (jurisdiction_type, jurisdiction_code, chamber, office, legal_domain, solution, procedure, publication, date_lecture_year, legal_instrument). Reuse keys verbatim as filter values. jurisdiction_code is capped to the top 15 courts (other_courts counts the rest) and legal_instrument to the top 10 statutes. chamber appears only under a jurisdiction_code filter, and then lists every formation of the selected courts." - removed
Output schema / properties / filterRewritten / descriptionRemoved value: -"A filter of the call was retired and rewritten: what was asked, what was searched, and the filter to use instead. The hits answer the rewritten call." - removed
Output schema / properties / hits / items / descriptionRemoved value: -"Metadata fields carry search_decisions filter tokens: each field matches the filter of the same name (jurisdictionType → jurisdiction_type, legalDomain → legal_domain…) and its value passes back verbatim to filter." - removed
Output schema / properties / hits / items / properties / aiSummary / descriptionRemoved value: -"AI-written summary of what the decision is about (semantic search), a machine paraphrase, NEVER the court's words: nothing in it is quotable. Exactly one of aiSummary/snippet is served per hit." - removed
Output schema / properties / hits / items / properties / chamberRemoved value: -{ - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null, - "description": "Chamber that heard the case, as \"<court>|<chamber>\", reusable verbatim as the chamber filter." -} - removed
Output schema / properties / hits / items / properties / officialUrl / descriptionRemoved value: -"The decision on its official publisher: legifrance.gouv.fr, courdecassation.fr, opendata.justice-administrative.fr, conseil-constitutionnel.fr, hudoc, eur-lex. Cite this when the deliverable requires the authoritative source; `url` is the LibreJustice page. Absent when the publisher exposes no per-decision permalink." - removed
Output schema / properties / hits / items / properties / publication / descriptionRemoved value: -"Publication values carried, reusable verbatim as the publication filter." - added
Output schema / properties / hits / items / properties / seatAdded value: +{ + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null +} - removed
Output schema / properties / hits / items / properties / snippet / descriptionRemoved value: -"Verbatim passage of the decision text where the query terms matched (keyword search). Exactly one of aiSummary/snippet is served per hit." - added
Output schema / properties / pinnedAdded value: +{ + "items": { + "additionalProperties": false, + "properties": { + "title": { + "type": "string" + }, + "url": { + "type": "string" + } + }, + "required": [ + "title", + "url" + ], + "type": "object" + }, + "type": "array" +} - removed
Output schema / properties / total / descriptionRemoved value: -"Decisions matched under the current filters, the whole set and not the served window: `hits` is one page of it, and `facets` counts that same set. Keyword matching is an OR bag over the query tokens, so a long query matches a large share of the corpus: narrow with filters (court, dates, chamber) rather than with more words for the number to count something."
- Changed
search_legal_texts1 field changed- removed
Output schema / properties / facets / descriptionRemoved value: -"Per filter name, a map of filter value to article count under the current query (code, jurisdiction). Reuse keys verbatim as filter values. Each axis is capped to its top 10."
4 tool updates
- Changed
get_decision3 fields changed- changed
Output schema / properties / appellateFate / descriptionPrevious value: -"Fate of THIS decision before the court that reviewed it, precomputed from caseChronology: 'INFIRMATION — Cour d'appel de Paris, 1 juillet 2025 (url)'. INFIRMATION = this decision was reversed and no longer stands; CONFIRMATION = upheld. Absent = no recourse known to the corpus, which never proves the decision is final."New value: +"Fate of THIS decision before the court that reviewed it, precomputed from caseChronology: 'INFIRMATION, Cour d'appel de Paris, 1 juillet 2025 (url)'. INFIRMATION = this decision was reversed and no longer stands; CONFIRMATION = upheld. Absent = no recourse known to the corpus, which never proves the decision is final." - changed
Output schema / properties / commentaires / descriptionPrevious value: -"Institutional commentary anchored on this document: court-written analyses served inline (`body`), plus outbound links (`url`) to the rapporteur public's conclusions and to related institutional documents (reports, opinions, press releases). Context, never the ruling itself — quote the decision text, not a commentaire, as the court's words."New value: +"Institutional commentary anchored on this document: court-written analyses served inline (`body`), plus outbound links (`url`) to the rapporteur public's conclusions and to related institutional documents (reports, opinions, press releases). Context, never the ruling itself. Quote the decision text, not a commentaire, as the court's words." - changed
Output schema / properties / commentaires / items / properties / url / descriptionPrevious value: -"External link, to hand to the user — not openable by an MCP tool."New value: +"External link, to hand to the user, not openable by an MCP tool."
- Changed
get_legal_text4 fields changed- changed
Input schema / properties / date / descriptionPrevious value: -"Consultation date (YYYY-MM-DD) — returns the version in force at that date. Omit for the version currently in force."New value: +"Consultation date (YYYY-MM-DD): returns the version in force at that date. Omit for the version currently in force." - changed
Input schema / properties / url / descriptionPrevious 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/{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." - changed
Output schema / properties / commentaires / descriptionPrevious value: -"Institutional commentary anchored on this document: court-written analyses served inline (`body`), plus outbound links (`url`) to the rapporteur public's conclusions and to related institutional documents (reports, opinions, press releases). Context, never the ruling itself — quote the decision text, not a commentaire, as the court's words."New value: +"Institutional commentary anchored on this document: court-written analyses served inline (`body`), plus outbound links (`url`) to the rapporteur public's conclusions and to related institutional documents (reports, opinions, press releases). Context, never the ruling itself. Quote the decision text, not a commentaire, as the court's words." - changed
Output schema / properties / commentaires / items / properties / url / descriptionPrevious value: -"External link, to hand to the user — not openable by an MCP tool."New value: +"External link, to hand to the user, not openable by an MCP tool."
- Changed
search_decisions6 fields changed- changed
Input schema / properties / ai_rerank / descriptionPrevious value: -"When 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."New value: +"When 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." - changed
Input schema / properties / legal_article / descriptionPrevious value: -"Restrict 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."New value: +"Restrict 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." - changed
Input schema / properties / limit / descriptionPrevious value: -"Maximum number of results (default 10). Above 20 the window is clamped, not refused."New value: +"Maximum number of results (default 10)." - changed
Input schema / properties / mode / descriptionPrevious 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. Never for a docket number or a decision name, which auto resolves by exact key. semantic: force the meaning+keyword hybrid even on quoted or operator queries (where auto would fall back to keyword-only). Naming a mode, like adding ET / OU / SAUF, also keeps a docket number inside an ordinary query instead of resolving it alone."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. Never for a docket number or a decision name, which auto resolves by exact key. semantic: force the meaning+keyword hybrid even on quoted or operator queries (where auto would fall back to keyword-only). Naming a mode, like adding ET / OU / SAUF, also keeps a docket number inside an ordinary query instead of resolving it alone." - changed
Input schema / properties / query / descriptionPrevious 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: a quoted phrase followed by free words requires every one of them in the same decision. (c) A docket number or a decision name takes neither quotes nor operators: « 21PA01295 », « n° 19-20.682 », « arrêt Danthony » are matched by an exact key, whatever the spelling, and quoting them only costs the recovery that catches a miss."New 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: a quoted phrase followed by free words requires every one of them in the same decision. (c) A docket number or a decision name takes neither quotes nor operators: « 21PA01295 », « n° 19-20.682 », « arrêt Danthony » are matched by an exact key, whatever the spelling, and quoting them only costs the recovery that catches a miss." - changed
Output schema / properties / hits / items / properties / aiSummary / descriptionPrevious value: -"AI-written summary of what the decision is about (semantic search) — a machine paraphrase, NEVER the court's words: nothing in it is quotable. Exactly one of aiSummary/snippet is served per hit."New value: +"AI-written summary of what the decision is about (semantic search), a machine paraphrase, NEVER the court's words: nothing in it is quotable. Exactly one of aiSummary/snippet is served per hit."
- Changed
search_legal_texts2 fields changed- changed
Input schema / properties / date / descriptionPrevious value: -"Consultation date (YYYY-MM-DD) — searches the versions valid at that date (point-in-time, same semantics as get_legal_text). Omit to search the versions currently in force."New value: +"Consultation date (YYYY-MM-DD): searches the versions valid at that date (point-in-time, same semantics as get_legal_text). Omit to search the versions currently in force." - changed
Input schema / properties / limit / descriptionPrevious value: -"Maximum number of results (default 10). Above 20 the window is clamped, not refused."New value: +"Maximum number of results (default 10)."
3 tool updates
- Changed
get_decision6 fields changed- changed
Output schema / properties / caseChronology / descriptionPrevious value: -"Linked prior and subsequent decisions of the same case (appeal, pourvoi, renvoi), most recent first, current decision included. The fate of a judgment reads in the solution of the decision that reviewed it (INFIRMATION = reversed, CONFIRMATION = upheld). Absent chronology never proves no recourse exists."New value: +"Prior and subsequent decisions of the same case (appeal, pourvoi, renvoi), most recent first, current decision included. The fate of a judgment reads in the solution of the decision that reviewed it (INFIRMATION = reversed, CONFIRMATION = upheld). Absent chronology never proves no recourse exists." - added
Output schema / properties / caseChronology / items / properties / url / anyOfAdded value: +[ + { + "type": "string" + }, + { + "type": "null" + } +] - added
Output schema / properties / caseChronology / items / properties / url / defaultAdded value: +null - added
Output schema / properties / caseChronology / items / properties / url / descriptionAdded value: +"Absent when the corpus does not hold that step: it is named by the decision that attacks it, and cannot be opened." - removed
Output schema / properties / caseChronology / items / properties / url / typeRemoved value: -"string" - changed
Output schema / properties / caseChronology / items / requiredPrevious value: -[ - "title", - "url", - "current" -]New value: +[ + "title", + "current" +]
- Changed
search_decisions6 fields changed- changed
Input schema / properties / chamber / descriptionPrevious value: -"Restrict to one or more chambers, as a composite key \"<court>|<chamber>\" where <court> is a jurisdiction_code (e.g. \"ca_paris|C3\", \"cc|C2\", \"cc|SOCIALE\"). The court prefix is required: a chamber key names a different chamber in each court, \"C1\" alone existing in about 200 of them. The chamber part reads as slots joined by a dot, in the order they render: \"P5\" (pôle 5), \"SC4\" (4e section, which contains chambers), \"C6\" (6e chambre), \"CD\" (chambre D), \"C4-7\" (chambre 4-7), \"S1\" (1re section), \"LB\" (section B), \"Q1-4\" (sous-sections 1/4 réunies), \"R3-8\" (chambres 3/8 réunies), numbers in a reunited list always ascending. So \"P5.C6\" is pôle 5, 6e chambre and \"C5.LA\" is section A of the 5th. A chamber that no coordinate positions is named by what it judges, and the key is that bare name, as at the Cour de cassation whose social and criminal chambers carry no number (\"cc|SOCIALE\", \"cc|CRIMINELLE\"). facets.chamber lists the pairs present in the current result set, and only once jurisdiction_code narrows it to one or more courts: a chamber key is meaningless outside its court, so search for the court first and read its formations from the answer."New value: +"Restrict to one or more chambers, as a composite key \"<court>|<chamber>\" where <court> is a jurisdiction_code (e.g. \"ca_paris|C3\", \"cc|C2\", \"cc|SOCIALE\"). The court prefix is required: a chamber key names a different chamber in each court, \"C1\" alone existing in about 200 of them. The chamber part is slots joined by a dot, in the order they render: tag P (pôle), SC (section holding chambers), C (chambre), S (section), L (lettered section), Q (sous-sections réunies) or R (chambres réunies), then its number or letter. So \"P5.C6\" is pôle 5, 6e chambre, \"C5.LA\" section A of the 5th, \"CD\" chambre D, \"R3-8\" chambres 3/8 réunies (numbers in a reunited list always ascending). A chamber that no coordinate positions is keyed by what it judges instead (\"cc|SOCIALE\", \"cc|CRIMINELLE\"). facets.chamber lists the pairs present, and only once jurisdiction_code narrows the search to one or more courts." - changed
Input schema / properties / limit / descriptionPrevious value: -"How many results to come back with. Keep the default of 10: the reranker has already put the best first, and each extra hit spends caller context on a preview that must not be quoted. Above 20 the window is clamped to 20, not refused."New value: +"Maximum number of results (default 10). Above 20 the window is clamped, not refused." - changed
Input schema / properties / mode / descriptionPrevious 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. Never for a docket number or a decision name, which auto resolves by exact key. 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. Never for a docket number or a decision name, which auto resolves by exact key. semantic: force the meaning+keyword hybrid even on quoted or operator queries (where auto would fall back to keyword-only). Naming a mode, like adding ET / OU / SAUF, also keeps a docket number inside an ordinary query instead of resolving it alone." - removed
Output schema / properties / absentReferenceRemoved value: -{ - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null, - "description": "Docket number asked for and not found: the hits below carry another number. Absent from the corpus when absentScope is null, absent from that scope only otherwise." -} - removed
Output schema / properties / absentScopeRemoved value: -{ - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null, - "description": "Court and year the call pinned around absentReference, when no decision carrying that number satisfies them: the number exists elsewhere in the corpus. Drop or widen that filter to reach it." -} - changed
Output schema / properties / facets / descriptionPrevious value: -"Per filter name, a map of filter value to decision count under the current query (jurisdiction_type, jurisdiction_code, chamber, office, legal_domain, solution, procedure, publication, date_lecture_year, legal_instrument). Reuse keys verbatim as filter values. jurisdiction_code is capped to the top 15 courts (other_courts counts the rest) and legal_instrument to the top 10 statutes. chamber appears only under a jurisdiction_code filter, and then lists every formation of the selected courts: search once for the court, once more for the chamber."New value: +"Per filter name, a map of filter value to decision count under the current query (jurisdiction_type, jurisdiction_code, chamber, office, legal_domain, solution, procedure, publication, date_lecture_year, legal_instrument). Reuse keys verbatim as filter values. jurisdiction_code is capped to the top 15 courts (other_courts counts the rest) and legal_instrument to the top 10 statutes. chamber appears only under a jurisdiction_code filter, and then lists every formation of the selected courts."
- Changed
search_legal_texts1 field changed- changed
Input schema / properties / limit / descriptionPrevious value: -"How many results to come back with. Keep the default of 10: the reranker has already put the best first, and each extra hit spends caller context on a preview that must not be quoted. Above 20 the window is clamped to 20, not refused."New value: +"Maximum number of results (default 10). Above 20 the window is clamped, not refused."
3 tool updates
- Changed
list_my_activity3 fields changed- changed
Output schema / descriptionPrevious value: -"Sortie unique de ``list_my_activity`` : chaque tranche n'est remplie que\nsi elle a été demandée (``kind`` ciblé ou ``all``). Un seul modèle à plat\n(plutôt qu'une union par ``kind``) évite une enveloppe ``result``. Noter\nqu'après inlining des ``$ref`` par ``_clean_schema`` (cf. mcp_server),\n``McpDecisionRef`` apparaît deux fois dans le schéma émis — une fois sous\n``bookmarks``, une fois sous ``readingHistory``."New value: +"One flat payload for every tab: a slice is filled only when it was asked for, by a targeted `kind` or by `all`." - changed
Output schema / properties / bookmarks / anyOfPrevious value: -[ - { - "additionalProperties": false, - "properties": { - "bookmarks": { - "items": { - "additionalProperties": false, - "description": "Référence décision pour signets/consultations : assez pour citer ou\nchaîner vers ``get_decision`` via ``url``, sans le texte intégral.", - "properties": { - "bookmarkedAt": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null, - "format": "date-time" - }, - "dateLecture": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null, - "format": "date" - }, - "lastSource": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null - }, - "lastViewedAt": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null, - "format": "date-time" - }, - "solution": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null - }, - "summary": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null - }, - "title": { - "type": "string" - }, - "url": { - "type": "string" - }, - "viewCount": { - "anyOf": [ - { - "type": "integer" - }, - { - "type": "null" - } - ], - "default": null - } - }, - "required": [ - "title", - "url" - ], - "type": "object" - }, - "type": "array" - }, - "total": { - "type": "integer" - } - }, - "required": [ - "total", - "bookmarks" - ], - "type": "object" - }, - { - "type": "null" - } -]New value: +[ + { + "additionalProperties": false, + "properties": { + "bookmarks": { + "items": { + "additionalProperties": false, + "description": "Decision reference for bookmarks and reading history: enough to cite it or to chain into get_decision with its `url`, without the full text.", + "properties": { + "bookmarkedAt": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "format": "date-time" + }, + "dateLecture": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "format": "date" + }, + "lastSource": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null + }, + "lastViewedAt": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "format": "date-time" + }, + "solution": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null + }, + "summary": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null + }, + "title": { + "type": "string" + }, + "url": { + "type": "string" + }, + "viewCount": { + "anyOf": [ + { + "type": "integer" + }, + { + "type": "null" + } + ], + "default": null + } + }, + "required": [ + "title", + "url" + ], + "type": "object" + }, + "type": "array" + }, + "total": { + "type": "integer" + } + }, + "required": [ + "total", + "bookmarks" + ], + "type": "object" + }, + { + "type": "null" + } +] - changed
Output schema / properties / readingHistory / anyOfPrevious value: -[ - { - "additionalProperties": false, - "properties": { - "decisions": { - "items": { - "additionalProperties": false, - "description": "Référence décision pour signets/consultations : assez pour citer ou\nchaîner vers ``get_decision`` via ``url``, sans le texte intégral.", - "properties": { - "bookmarkedAt": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null, - "format": "date-time" - }, - "dateLecture": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null, - "format": "date" - }, - "lastSource": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null - }, - "lastViewedAt": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null, - "format": "date-time" - }, - "solution": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null - }, - "summary": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null - }, - "title": { - "type": "string" - }, - "url": { - "type": "string" - }, - "viewCount": { - "anyOf": [ - { - "type": "integer" - }, - { - "type": "null" - } - ], - "default": null - } - }, - "required": [ - "title", - "url" - ], - "type": "object" - }, - "type": "array" - }, - "total": { - "type": "integer" - } - }, - "required": [ - "total", - "decisions" - ], - "type": "object" - }, - { - "type": "null" - } -]New value: +[ + { + "additionalProperties": false, + "properties": { + "decisions": { + "items": { + "additionalProperties": false, + "description": "Decision reference for bookmarks and reading history: enough to cite it or to chain into get_decision with its `url`, without the full text.", + "properties": { + "bookmarkedAt": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "format": "date-time" + }, + "dateLecture": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "format": "date" + }, + "lastSource": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null + }, + "lastViewedAt": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "format": "date-time" + }, + "solution": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null + }, + "summary": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null + }, + "title": { + "type": "string" + }, + "url": { + "type": "string" + }, + "viewCount": { + "anyOf": [ + { + "type": "integer" + }, + { + "type": "null" + } + ], + "default": null + } + }, + "required": [ + "title", + "url" + ], + "type": "object" + }, + "type": "array" + }, + "total": { + "type": "integer" + } + }, + "required": [ + "total", + "decisions" + ], + "type": "object" + }, + { + "type": "null" + } +]
- Changed
search_decisions3 fields changed- changed
Input schema / properties / chamber / descriptionPrevious value: -"Restrict to one or more chambers, as a composite key \"<court>|<chamber>\" where <court> is a jurisdiction_code (e.g. \"ca_paris|CH:3\", \"cc|CH:2\", \"cc|MAT:SOCIALE\"). The court prefix is required: a chamber key names a different chamber in each court, \"CH:1\" alone existing in about 200 of them. The chamber part is what names the chamber inside its own court: its position in the organisation chart when it has one, \"CH:2\" (2e chambre), \"CH:5.A\" (section A of the 5th), \"P:1-11\" (pôle 1, 11e chambre), \"CHC:4-7\" (chambre 4-7), \"S:8\" (8e section), \"SS:3\" (3e sous-section), \"SSR:1-4\" and \"CHR:3-8\" (reunited, numbers always ascending); its specialisation otherwise, prefixed \"MAT:\", as at the Cour de cassation whose social and criminal chambers carry no number (\"cc|MAT:SOCIALE\", \"cc|MAT:CRIMINELLE\"). facets.chamber lists the pairs present in the current result set."New value: +"Restrict to one or more chambers, as a composite key \"<court>|<chamber>\" where <court> is a jurisdiction_code (e.g. \"ca_paris|C3\", \"cc|C2\", \"cc|SOCIALE\"). The court prefix is required: a chamber key names a different chamber in each court, \"C1\" alone existing in about 200 of them. The chamber part reads as slots joined by a dot, in the order they render: \"P5\" (pôle 5), \"SC4\" (4e section, which contains chambers), \"C6\" (6e chambre), \"CD\" (chambre D), \"C4-7\" (chambre 4-7), \"S1\" (1re section), \"LB\" (section B), \"Q1-4\" (sous-sections 1/4 réunies), \"R3-8\" (chambres 3/8 réunies), numbers in a reunited list always ascending. So \"P5.C6\" is pôle 5, 6e chambre and \"C5.LA\" is section A of the 5th. A chamber that no coordinate positions is named by what it judges, and the key is that bare name, as at the Cour de cassation whose social and criminal chambers carry no number (\"cc|SOCIALE\", \"cc|CRIMINELLE\"). facets.chamber lists the pairs present in the current result set, and only once jurisdiction_code narrows it to one or more courts: a chamber key is meaningless outside its court, so search for the court first and read its formations from the answer." - changed
Input schema / properties / limit / descriptionPrevious value: -"Maximum number of results (1–20, default 10)."New value: +"How many results to come back with. Keep the default of 10: the reranker has already put the best first, and each extra hit spends caller context on a preview that must not be quoted. Above 20 the window is clamped to 20, not refused." - changed
Output schema / properties / facets / descriptionPrevious value: -"Per filter name, a map of filter value to decision count under the current query (jurisdiction_type, jurisdiction_code, chamber, office, legal_domain, solution, procedure, publication, date_lecture_year, legal_instrument). Reuse keys verbatim as filter values. jurisdiction_code is capped to the top 15 courts (other_courts counts the rest), chamber to the top 15 chambers (other_chambers), legal_instrument to the top 10 statutes."New value: +"Per filter name, a map of filter value to decision count under the current query (jurisdiction_type, jurisdiction_code, chamber, office, legal_domain, solution, procedure, publication, date_lecture_year, legal_instrument). Reuse keys verbatim as filter values. jurisdiction_code is capped to the top 15 courts (other_courts counts the rest) and legal_instrument to the top 10 statutes. chamber appears only under a jurisdiction_code filter, and then lists every formation of the selected courts: search once for the court, once more for the chamber."
- Changed
search_legal_texts1 field changed- changed
Input schema / properties / limit / descriptionPrevious value: -"Maximum number of results (1–20, default 10)."New value: +"How many results to come back with. Keep the default of 10: the reranker has already put the best first, and each extra hit spends caller context on a preview that must not be quoted. Above 20 the window is clamped to 20, not refused."
1 tool update
- Changed
search_decisions4 fields changed- changed
Input schema / properties / mode / descriptionPrevious 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. The right choice when searching for a named entity (company, municipality, person), a precise legal formula, or an exact quote — cuts semantic noise. 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. Never for a docket number or a decision name, which auto resolves by exact key. semantic: force the meaning+keyword hybrid even on quoted or operator queries (where auto would fall back to keyword-only)." - changed
Input schema / properties / query / descriptionPrevious 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: +"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: a quoted phrase followed by free words requires every one of them in the same decision. (c) A docket number or a decision name takes neither quotes nor operators: « 21PA01295 », « n° 19-20.682 », « arrêt Danthony » are matched by an exact key, whatever the spelling, and quoting them only costs the recovery that catches a miss." - changed
Output schema / properties / absentReference / descriptionPrevious value: -"Docket number asked for and absent from the corpus: the hits below carry another number."New value: +"Docket number asked for and not found: the hits below carry another number. Absent from the corpus when absentScope is null, absent from that scope only otherwise." - added
Output schema / properties / absentScopeAdded value: +{ + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "Court and year the call pinned around absentReference, when no decision carrying that number satisfies them: the number exists elsewhere in the corpus. Drop or widen that filter to reach it." +}
1 tool update
- Changed
search_decisions2 fields changed- added
Output schema / properties / totalAdded value: +{ + "description": "Decisions matched under the current filters, the whole set and not the served window: `hits` is one page of it, and `facets` counts that same set. Keyword matching is an OR bag over the query tokens, so a long query matches a large share of the corpus: narrow with filters (court, dates, chamber) rather than with more words for the number to count something.", + "type": "integer" +} - changed
Output schema / requiredPrevious value: -[ - "query", - "hits" -]New value: +[ + "query", + "total", + "hits" +]
1 tool update
- Changed
get_legal_text4 fields changed- added
Output schema / properties / articleCountAdded value: +{ + "description": "Number of articles the text carries. Present only on the root of a text with articles.", + "type": "integer" +} - added
Output schema / properties / articlesAdded value: +{ + "description": "Contents of a text root or of one of its divisions, in reading order. Each `url` goes back to get_legal_text; a `section` entry returns all its articles at once, which is the cheapest way to read a chapter. `text` is joined only within the inline reading budget.", + "items": { + "additionalProperties": false, + "properties": { + "kind": { + "enum": [ + "article", + "section" + ], + "type": "string" + }, + "num": { + "description": "Article number, or the division title when `kind` is `section`.", + "type": "string" + }, + "section": { + "type": "string" + }, + "text": { + "type": "string" + }, + "url": { + "type": "string" + } + }, + "required": [ + "kind", + "num", + "url" + ], + "type": "object" + }, + "type": "array" +} - changed
Output schema / properties / num / descriptionPrevious value: -"Article key. Absent when the url addressed a text with no articles: the payload is then the whole text, `text` carrying its body and `versions` empty."New value: +"Article key. Absent when the url addressed the root of a text: with no articles the payload is the whole text, `text` carrying its body; with articles it is the table of contents, `articles` carrying it." - added
Output schema / properties / omittedAdded value: +{ + "description": "Articles served without their body because the text or division exceeds the inline reading budget: their `url` fetches them.", + "type": "integer" +}
1 tool update
- Changed
search_decisions1 field changed- changed
Input schema / properties / office / anyOfPrevious value: -[ - { - "items": { - "enum": [ - "JLD", - "JAF", - "JCP", - "JEX", - "JUGE_ENFANTS", - "PREMIER_PRESIDENT", - "MAGISTRAT_DESIGNE" - ], - "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" + ], + "type": "string" + }, + "type": "array" + }, + { + "type": "null" + } +]
2 tool updates
- Changed
get_decision1 field changed- removed
Output schema / properties / matiereRemoved value: -{ - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null -}
- Changed
search_decisions5 fields changed- changed
Input schema / properties / jurisdiction_code / descriptionPrevious value: -"Restrict to one or more precise court units by referential code. Code shapes: \"cc\" (Cour de cassation), \"ce\" (Conseil d'État), \"cnda\", \"cedh\", \"cjue\"; \"ca_<city>\", \"caa_<city>\", \"ta_<city>\", \"tj_<city>\", \"tcom_<city>\" (e.g. \"ca_paris\", \"ta_marseille\", \"tj_paris\", \"tcom_lyon\"). When unsure, guess with the city name in the code: the error names the nearest valid ones. Each code is a court; the chamber inside it is a separate filter (see chamber and matiere); use jurisdiction_type for the broad category."New value: +"Restrict to one or more precise court units by referential code. Code shapes: \"cc\" (Cour de cassation), \"ce\" (Conseil d'État), \"cnda\", \"cedh\", \"cjue\"; \"ca_<city>\", \"caa_<city>\", \"ta_<city>\", \"tj_<city>\", \"tcom_<city>\" (e.g. \"ca_paris\", \"ta_marseille\", \"tj_paris\", \"tcom_lyon\"). When unsure, guess with the city name in the code: the error names the nearest valid ones. Each code is a court; the chamber inside it is a separate filter (see chamber); use jurisdiction_type for the broad category." - removed
Input schema / properties / matiereRemoved value: -{ - "anyOf": [ - { - "items": { - "enum": [ - "BAUX", - "CIVI", - "CIVILE", - "COMMERCIALE", - "CONSEIL", - "CONSTRUCTION", - "COPROPRIETE", - "CORRECTIONNELLE", - "CRIMINELLE", - "DALO", - "ETRANGERS", - "EXPROPRIATION", - "FAMILLE", - "INSTRUCTION", - "MINEURS", - "NATIONALITE", - "PROCEDURES_COLLECTIVES", - "PROTECTION_SOCIALE", - "PROXIMITE", - "PRUD_HOMALE", - "SOCIALE", - "SURENDETTEMENT", - "TERRES", - "URGENCES" - ], - "type": "string" - }, - "maxItems": 10, - "type": "array" - }, - { - "type": "null" - } - ], - "default": null, - "description": "Filter by subject matter (any-of, uniform across orders): the contentieux the case belongs to, read off the chamber that heard it, independent of the court itself. Pairs with office for the single-judge formations. Where a court names its chambers instead of numbering them, this says the same thing as chamber does (\"cc|MAT:SOCIALE\"), matiere being the one that crosses courts. A general matiere covers its specialities: \"CIVILE\" also returns BAUX, COPROPRIETE and FAMILLE, while a speciality returns itself alone." -} - changed
Output schema / properties / facets / descriptionPrevious value: -"Per filter name, a map of filter value to decision count under the current query (jurisdiction_type, jurisdiction_code, matiere, chamber, office, legal_domain, solution, procedure, publication, date_lecture_year, legal_instrument). Reuse keys verbatim as filter values. jurisdiction_code is capped to the top 15 courts (other_courts counts the rest), chamber to the top 15 chambers (other_chambers), legal_instrument to the top 10 statutes."New value: +"Per filter name, a map of filter value to decision count under the current query (jurisdiction_type, jurisdiction_code, chamber, office, legal_domain, solution, procedure, publication, date_lecture_year, legal_instrument). Reuse keys verbatim as filter values. jurisdiction_code is capped to the top 15 courts (other_courts counts the rest), chamber to the top 15 chambers (other_chambers), legal_instrument to the top 10 statutes." - added
Output schema / properties / filterRewrittenAdded value: +{ + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "A filter of the call was retired and rewritten: what was asked, what was searched, and the filter to use instead. The hits answer the rewritten call." +} - removed
Output schema / properties / hits / items / properties / matiereRemoved value: -{ - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null -}
1 tool update
- Changed
search_decisions2 fields changed- changed
Input schema / properties / matiere / descriptionPrevious value: -"Filter by subject matter (any-of, uniform across orders): the contentieux the case belongs to, read off the chamber that heard it, independent of the court itself. Pairs with office for the single-judge formations. Where a court names its chambers instead of numbering them, this says the same thing as chamber does (\"cc|MAT:SOCIALE\"), matiere being the one that crosses courts."New value: +"Filter by subject matter (any-of, uniform across orders): the contentieux the case belongs to, read off the chamber that heard it, independent of the court itself. Pairs with office for the single-judge formations. Where a court names its chambers instead of numbering them, this says the same thing as chamber does (\"cc|MAT:SOCIALE\"), matiere being the one that crosses courts. A general matiere covers its specialities: \"CIVILE\" also returns BAUX, COPROPRIETE and FAMILLE, while a speciality returns itself alone." - changed
Output schema / properties / facets / descriptionPrevious value: -"Per filter name, a map of filter value to decision count under the current query (jurisdiction_type, jurisdiction_code, matiere, chamber, office, legal_domain, solution, publication, date_lecture_year, legal_instrument). Reuse keys verbatim as filter values. jurisdiction_code is capped to the top 15 courts (other_courts counts the rest), chamber to the top 15 chambers (other_chambers), legal_instrument to the top 10 statutes."New value: +"Per filter name, a map of filter value to decision count under the current query (jurisdiction_type, jurisdiction_code, matiere, chamber, office, legal_domain, solution, procedure, publication, date_lecture_year, legal_instrument). Reuse keys verbatim as filter values. jurisdiction_code is capped to the top 15 courts (other_courts counts the rest), chamber to the top 15 chambers (other_chambers), legal_instrument to the top 10 statutes."
2 tool updates
- Changed
get_decision1 field changed- changed
Output schema / properties / chamber / descriptionPrevious value: -"Bench that heard the case, as \"<court>|<bench>\", reusable verbatim as the chamber filter."New value: +"Chamber that heard the case, as \"<court>|<chamber>\", reusable verbatim as the chamber filter."
- Changed
search_decisions5 fields changed- changed
Input schema / properties / chamber / descriptionPrevious value: -"Restrict to one or more benches, as a composite key \"<court>|<bench>\" where <court> is a jurisdiction_code (e.g. \"ca_paris|CH:3\", \"cc|CH:2\"). The court prefix is required: a bench key names a different bench in each court, \"CH:1\" alone existing in about 200 of them. The bench part is a position in the court's own organisation chart, not a subject (that is matiere): \"CH:2\" (2e chambre), \"CH:5.A\" (section A of the 5th), \"P:1-11\" (pôle 1, 11e chambre), \"CHC:4-7\" (chambre 4-7), \"S:8\" (8e section), \"SS:3\" (3e sous-section), \"SSR:1-4\" and \"CHR:3-8\" (reunited, numbers always ascending). facets.chamber lists the pairs present in the current result set."New value: +"Restrict to one or more chambers, as a composite key \"<court>|<chamber>\" where <court> is a jurisdiction_code (e.g. \"ca_paris|CH:3\", \"cc|CH:2\", \"cc|MAT:SOCIALE\"). The court prefix is required: a chamber key names a different chamber in each court, \"CH:1\" alone existing in about 200 of them. The chamber part is what names the chamber inside its own court: its position in the organisation chart when it has one, \"CH:2\" (2e chambre), \"CH:5.A\" (section A of the 5th), \"P:1-11\" (pôle 1, 11e chambre), \"CHC:4-7\" (chambre 4-7), \"S:8\" (8e section), \"SS:3\" (3e sous-section), \"SSR:1-4\" and \"CHR:3-8\" (reunited, numbers always ascending); its specialisation otherwise, prefixed \"MAT:\", as at the Cour de cassation whose social and criminal chambers carry no number (\"cc|MAT:SOCIALE\", \"cc|MAT:CRIMINELLE\"). facets.chamber lists the pairs present in the current result set." - changed
Input schema / properties / jurisdiction_code / descriptionPrevious value: -"Restrict to one or more precise court units by referential code. Code shapes: \"cc\" (Cour de cassation), \"ce\" (Conseil d'État), \"cnda\", \"cedh\", \"cjue\"; \"ca_<city>\", \"caa_<city>\", \"ta_<city>\", \"tj_<city>\", \"tcom_<city>\" (e.g. \"ca_paris\", \"ta_marseille\", \"tj_paris\", \"tcom_lyon\"). When unsure, guess with the city name in the code: the error names the nearest valid ones. Each code is a court; the bench is a separate axis (see chamber and matiere); use jurisdiction_type for the broad category."New value: +"Restrict to one or more precise court units by referential code. Code shapes: \"cc\" (Cour de cassation), \"ce\" (Conseil d'État), \"cnda\", \"cedh\", \"cjue\"; \"ca_<city>\", \"caa_<city>\", \"ta_<city>\", \"tj_<city>\", \"tcom_<city>\" (e.g. \"ca_paris\", \"ta_marseille\", \"tj_paris\", \"tcom_lyon\"). When unsure, guess with the city name in the code: the error names the nearest valid ones. Each code is a court; the chamber inside it is a separate filter (see chamber and matiere); use jurisdiction_type for the broad category." - changed
Input schema / properties / matiere / descriptionPrevious value: -"Filter by subject matter (any-of, uniform across orders): the contentieux the case belongs to, read off the bench that heard it, independent of the court itself. Pairs with office for the single-judge benches, and with chamber for the bench itself."New value: +"Filter by subject matter (any-of, uniform across orders): the contentieux the case belongs to, read off the chamber that heard it, independent of the court itself. Pairs with office for the single-judge formations. Where a court names its chambers instead of numbering them, this says the same thing as chamber does (\"cc|MAT:SOCIALE\"), matiere being the one that crosses courts." - changed
Output schema / properties / facets / descriptionPrevious value: -"Per filter name, a map of filter value to decision count under the current query (jurisdiction_type, jurisdiction_code, matiere, chamber, office, legal_domain, solution, publication, date_lecture_year, legal_instrument). Reuse keys verbatim as filter values. jurisdiction_code is capped to the top 15 courts (other_courts counts the rest), chamber to the top 15 benches (other_benches), legal_instrument to the top 10 statutes."New value: +"Per filter name, a map of filter value to decision count under the current query (jurisdiction_type, jurisdiction_code, matiere, chamber, office, legal_domain, solution, publication, date_lecture_year, legal_instrument). Reuse keys verbatim as filter values. jurisdiction_code is capped to the top 15 courts (other_courts counts the rest), chamber to the top 15 chambers (other_chambers), legal_instrument to the top 10 statutes." - changed
Output schema / properties / hits / items / properties / chamber / descriptionPrevious value: -"Bench that heard the case, as \"<court>|<bench>\", reusable verbatim as the chamber filter."New value: +"Chamber that heard the case, as \"<court>|<chamber>\", reusable verbatim as the chamber filter."
Related MCP Connectors
French legal research: statutes in force at any date, case law both ways, verified citations.
Search 18M+ legal documents worldwide — case law, legislation, and doctrine across 110+ countries.
Search national and EU case law, legislation and regulation, with citations you can verify.
Search French companies: financials, directors, ownership, M&A and insolvency events.
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceEnables legal research by providing unified search across ~3.3 million court decisions (French and European) and ~1.5 million consolidated law articles, with tools for retrieving full texts and historical versions, all without authentication.10MIT
- AlicenseNot gradedqualityDmaintenanceEnables querying and retrieving legal texts and decisions from French public APIs Légifrance and JudiLibre for legal research.MIT
- AlicenseNot gradedqualityDmaintenanceProvides access to official French legal databases (Légifrance and JudiLibre) to search and retrieve French legislation, legal codes, case law, and judicial decisions through authenticated APIs.33MIT
- AlicenseNot gradedqualityFmaintenanceEnables AI assistants to search and retrieve French legislation, case law, and EU law integrations from official sources via MCP.64 npm1Apache 2.0
Glama MCP Gateway
Add one secure layer between your agents and this server.