Skip to main content
Glama

search_legi

Read-only

Recherche pondérée dans les codes et lois consolidés français.

Source : bulk LEGI DILA (3,6 Go avec versions historiques). Trouve
les articles dont le texte ou le titre contient les mots-clés.

⚠️ `titre_texte` est le titre du TEXTE contenant l'article (« Code civil »,
« Arrêté du 10 août 1998 »), PAS celui de sa section : la hiérarchie des
sections LEGI n'est pas ingérée dans le bulk. Pour situer un article dans
le plan d'un code (partie / livre / titre / chapitre / section), il faut
consulter Légifrance — l'ancien champ `titre_section` renvoyait le titre du
code et donnait l'illusion d'une réponse.

Sans filtre `code`, les résultats sont DÉDUPLIQUÉS par texte-parent (un
article par texte, le mieux classé) : `returned` peut donc être bien
inférieur à `total` sans que rien ne manque — c'est le sens de
`deduplicated_by`. Avec un filtre `code`, aucune dédup.

Args:
    query: mots-clés FTS5
    code: filtre optionnel — sigle (CC, CT, CSP, COJ…) ou LEGITEXT/JORFTEXT
        direct. Un sigle inconnu renvoie une erreur explicite (et non,
        comme avant, une recherche non filtrée déguisée en succès).
    date_min/date_max: filtre par date_debut de version (ISO)
    limit: max 50
    offset: pagination

Returns:
    {"total", "returned", "articles": [...]}

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
codeNo
limitNo
queryYes
offsetNo
date_maxNo
date_minNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

TDQS

A4.3/5.0
Behavior5/5

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

Even with readOnlyHint=true, the description adds substantial behavioral context: weighted search, deduplication by parent text, the meaning of returned vs total, the titre_texte caveat about LEGI section hierarchy, explicit error behavior for unknown code sigles, limit max 50, and date filter semantics. It even discloses a past misleading behavior (titre_section).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but well-structured, with purpose, source, caveats, args, and returns clearly separated. Each sentence adds value, and the warnings are important. It is slightly long but not padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return values need not be explained, but the description still includes them. It covers source context, deduplication semantics, field caveats, parameter constraints, and error behavior. An agent has everything needed to select and invoke this tool correctly.

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

Parameters5/5

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

Schema description coverage is 0%, and the description fully compensates with an Args section explaining every parameter: query (FTS5 keywords), code (sigle or LEGITEXT/JORFTEXT, error on unknown), date_min/date_max (ISO version start date), limit (max 50), and offset (pagination). This goes well beyond the bare schema.

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

Purpose4/5

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

The description states a specific verb and resource: 'Recherche pondérée dans les codes et lois consolidés français' and 'Trouve les articles dont le texte ou le titre contient les mots-clés.' This clearly distinguishes it from decision-focused or journal-officiel search tools, though it does not explicitly name a sibling alternative.

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

Usage Guidelines3/5

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

The intended use is implied through the resource description (LEGI codes/laws) and extensive notes about filtering and deduplication. However, there is no explicit guidance about when to use this tool versus siblings like search_all, get_law_article, or search_jorf.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0
Disambiguation4/5

The tools are mostly distinct by legal source (admin, CC, CEDH, CJUE, etc.) and by action (search vs. retrieve). However, pairs like search_admin vs. search_conseil_etat both target Council of State jurisprudence, and get_decision_text could be mistaken for a generic decision retriever, creating some potential confusion despite detailed descriptions.

Naming Consistency5/5

All tool names follow a consistent lowercase snake_case pattern with action-first naming (get_, search_, list_, build_, resolve_, about_). The get_decision_* and search_* prefixes clearly separate retrieval from search, and modifiers like _libre and _recent are applied systematically.

Tool Count2/5

With 31 tools, the server is heavy, exceeding the 25+ threshold for 'too many.' While the breadth of French legal sources justifies many search/retrieval tools, the three recent admin variants and the redundant PISTE vs. libre duplicates suggest the set could be consolidated. The count feels disproportionate to the core purpose of legal research.

Completeness4/5

The tool set covers the full read lifecycle for legal research: orientation (about), search across all major sources, full-text retrieval for each source, law article lookup with historical versions, and URL building. Minor gaps exist, such as lacking a structured code browse or a direct way to enumerate all articles in a section, but these are workarounds via search_legi and get_law_article.

Resources