Skip to main content
Glama

get_rappels_produits_actifs

Retourne les rappels et retraits de lots de produits alimentaires actifs en France en temps réel depuis RappelConso (DGCCRF). Source officielle : data.economie.gouv.fr (dataset rappelconso-v2-gtin-trie). Utilisez ce tool pour vérifier la sécurité alimentaire d'un produit avant service, savoir si une référence fait l'objet d'un rappel ou retrait de lots en cours, ou consulter les dernières alertes sanitaires officielles publiées par la Direction Générale de la Concurrence, de la Consommation et de la Répression des fraudes.

[EN] Returns active French food-product recalls in real time from RappelConso (DGCCRF open data). Filters: 'categorie', 'limit', 'date_depuis'.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoNombre maximum de rappels à retourner (défaut 10, maximum 50). Les plus récents en premier.
categorieNoFiltre optionnel par catégorie d'aliment. Valeurs : 'viande', 'poisson', 'produits_laitiers', 'boulangerie', 'epicerie', 'tous'. Si absent ou 'tous', renvoie toutes les catégories alimentaires.
date_depuisNoDate de publication minimale des rappels au format YYYY-MM-DD. Si absent, renvoie les plus récents sans limite de date.

TDQS

A4.1/5.0
Behavior4/5

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

There are no annotations, so the description carries the burden of disclosing behavior. It clearly states the tool returns only active recalls in real time from an official source, which conveys the temporal scope and data provenance. It does not describe response format or error behavior, but for a read-only retrieval tool this is adequate.

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 front-loaded with the core purpose and then adds the data source and use cases. The bilingual English sentence is somewhat redundant but not excessive. Overall, it is concise enough while remaining informative.

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

Completeness4/5

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

Given the tool has no output schema and no annotations, the description covers the main contextual needs: source, temporal scope, and when to use it. It lacks details about the exact response shape, but the described use cases and parameter information allow an agent to select and invoke the tool correctly.

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

Parameters3/5

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

The input schema already has 100% coverage with detailed descriptions for all three parameters (limit, categorie, date_depuis). The description merely lists the filter names without adding new meaning beyond the schema, so it meets the baseline but does not exceed it.

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

Purpose5/5

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

The description explicitly states that the tool returns active French food-product recalls in real time from the official RappelConso (DGCCRF) dataset. It names the specific resource and distinguishes this tool from sibling tools like get_rappels_par_categorie_etablissement by focusing on active recalls/pulls and the official data source.

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

Usage Guidelines4/5

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

The description provides clear use cases: checking food safety before service, determining if a product reference is recalled, and consulting the latest official health alerts. It does not explicitly mention when not to use this tool or name an alternative, but the intended context is well defined.

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

A3.9/5.0
Disambiguation4/5

Most tools have a clearly distinct purpose, but there are a few potentially confusable pairs: get_haccp_temperatures vs get_temperatures_cuisson, get_score_alimconfiance vs get_alimconfiance_etablissement, and get_rappels_produits_actifs vs get_rappels_par_categorie_etablissement. The descriptions explicitly cross-reference these, reducing ambiguity, but an agent could still misselect without careful reading.

Naming Consistency4/5

18 of 19 tools follow the consistent 'get_' + noun pattern (e.g., get_actions_correctives, get_seuils_microbiologiques). The lone exception is 'compare_solutions_haccp', which uses a different verb but still follows a verb_noun structure. This minor deviation keeps the set mostly predictable.

Tool Count3/5

With 19 tools, the count sits in the borderline-heavy range (16-25). The breadth is justified for a comprehensive HACCP regulatory assistant, but some tools like compare_solutions_haccp feel peripheral to the core compliance theme, making the set feel slightly overstuffed.

Completeness4/5

The set covers the HACCP domain extensively: temperatures, cooking, DLC, allergens, recalls, cleaning plans, checklists, corrective actions, DDPP documents, sanctions, training, and Alim'confiance. Minor gaps exist, such as no tool for generating a full HACCP plan document or tracking ongoing temperature logs, but for an informational/regulatory lookup server, coverage is strong.

Resources