Query a live PrestaShop e-commerce store: search the catalog, get product details, real-time prices and stock. Fondouk is an open-source module (MIT) that makes any PrestaShop store speak MCP and UCP — this connector is its public demo store. Read-only, public data only.
Scored across 3 tools
Each tool has a clearly distinct purpose: search_catalog finds products by text, lookup_catalog fetches by known IDs in bulk, and get_product retrieves one product's full details. The descriptions explicitly state when to use each, leaving no ambiguity.
All tool names follow the same lowercase snake_case verb_noun pattern: get_product, lookup_catalog, search_catalog. The verbs correspond well to their actions, making the naming predictable and readable.
With 3 tools, the set is small but appropriate for a read-only catalog lookup server. Every tool serves a distinct retrieval need, though the count is at the lower end of what feels substantial.
The toolset covers the full lookup workflow: search by criteria, batch fetch by IDs, and single-product details. Minor gaps exist, such as no direct category browsing or inventory listing, but these are not essential given the search filters and read-only scope.
Récupère les détails complets d'UN produit à partir de son identifiant (obtenu via search_catalog ou lookup_catalog). À utiliser lorsque le client souhaite les détails, les déclinaisons ou la disponibilité d'un produit précis. Renvoie une erreur "not_found" claire si l'identifiant ne correspond à aucun produit public. Lecture seule.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Identifiant de produit ou de déclinaison. | |
| context | No | Localisation facultative : langue (BCP 47), devise (ISO 4217), address_country (ISO 3166-1 alpha-2). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It clearly states read-only nature ('Lecture seule'), error behavior ('not_found' error), and the scope of output (details, variants, availability), which is strong context beyond the schema.
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 three sentences, each earning its place: purpose, usage, and error/behavior. It is front-loaded with the action and contains no filler or redundancy.
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's moderate complexity (one required parameter plus optional context object) and absence of an output schema, the description adequately covers purpose, usage, error handling, and read-only status. It would benefit from a hint about the exact return structure, but the mention of 'details, variants, availability' mitigates this.
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 value by explaining that the 'id' parameter comes from search_catalog or lookup_catalog, providing provenance and usage context that the schema alone does not convey.
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 clearly states the tool retrieves complete details of one product by ID, using a specific verb and resource. It distinguishes from siblings by referencing search_catalog and lookup_catalog as the source for the ID, making it clear this is for fetching a specific product's details.
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 states when to use the tool ('when the client wants details, variants, or availability of a specific product') and implies that the ID comes from sibling tools. However, it does not explicitly mention when not to use it, so it misses the full 'when-not' guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Récupère plusieurs produits par identifiants en un seul appel (lot). À utiliser lorsque vous disposez DÉJÀ des identifiants de produits/déclinaisons et souhaitez leur prix/disponibilité actuels. 100 identifiants maximum. Lecture seule.
| Name | Required | Description | Default |
|---|---|---|---|
| ids | Yes | ||
| context | No | Localisation facultative : langue (BCP 47), devise (ISO 4217), address_country (ISO 3166-1 alpha-2). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses 'Lecture seule' (read-only) and a 100-ID maximum, which are valuable behavioral constraints. However, it does not mention error handling for invalid/unknown IDs, behavior when exceeding the limit, or the exact response structure, leaving some gaps.
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 four short sentences, each with a distinct purpose: main action, usage context, batch limit, and read-only nature. It is front-loaded with the verb and resource, contains no filler, and is easy to scan.
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 batch lookup tool, it covers purpose, usage, limit, read-only status, and hints at return content (price/availability). Since there is no output schema, a bit more detail on the response shape would help, but the description is still reasonably complete for this moderate complexity tool.
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 coverage is 50%: the context parameter has detailed descriptions, but ids lacks formatting details. The description adds meaning by clarifying IDs refer to products/variants and by imposing the 100-identifier limit. Still, it does not fully compensate for the missing ids format or context default behavior.
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: 'Récupère plusieurs produits par identifiants en un seul appel (lot)' clearly indicating batch retrieval. It also explicitly distinguishes itself from siblings by focusing on existing product/variant IDs and returning current price/availability, contrasting with a search-oriented tool.
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 provides explicit guidance: use when you already have IDs and need current price/availability. It implies this is for batch lookup rather than search, but it does not explicitly name alternatives or state when not to use it (e.g., for single ID retrieval), so a stronger contrast would improve it slightly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recherche des produits dans le catalogue PUBLIC du marchand par texte libre et filtres facultatifs (catégories, prix). À utiliser lorsque vous n'avez PAS d'identifiant de produit — p. ex. « chaussures de running bleues à moins de 100 € ». Renvoie des produits avec prix (TTC), déclinaisons et disponibilité. Paginé (curseur). Lecture seule.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | Texte de recherche libre. | |
| context | No | Localisation facultative : langue (BCP 47), devise (ISO 4217), address_country (ISO 3166-1 alpha-2). | |
| filters | No | p. ex. {"categories":["3"],"price":{"max":10000}} (prix en unités mineures). | |
| pagination | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Aucune annotation n'est fournie, la description assume donc pleinement la charge de transparence. Elle précise que l'outil est en lecture seule (« Lecture seule »), détaille les retours (prix TTC, déclinaisons, disponibilité) et signale la pagination par curseur, ce qui est utile. Il manque des détails comme les limites de taux ou les exigences d'authentification, mais l'essentiel est couvert.
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?
La description est concise en deux phrases, avec l'information la plus importante (but et cas d'usage) en tête. Chaque phrase apporte une valeur : le but, le moment d'utilisation, les retours et la pagination. Aucune redondance ni longueur excessive.
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?
Malgré l'absence de schéma de sortie, la description décrit suffisamment les retours (produits avec prix, déclinaisons, disponibilité) et le comportement de pagination. Elle couvre le but, le contexte d'utilisation, les paramètres facultatifs et la nature en lecture seule, ce qui rend l'outil compréhensible pour un agent dans la plupart des cas.
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?
La couverture du schéma est élevée (75 %), donc la baseline est de 3. La description ajoute peu d'information supplémentaire sur les paramètres au-delà du schéma : elle mentionne le texte libre, les filtres par catégories/prix et la pagination, mais le schéma fournit déjà ces détails avec des exemples. Aucune explication supplémentaire n'est donnée pour le paramètre 'context'.
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?
La description utilise un verbe spécifique (« Recherche ») et une ressource claire (« produits dans le catalogue PUBLIC du marchand »), ce qui distingue bien l'outil des outils frères comme get_product (qui nécessite un identifiant) et lookup_catalog. La mention explicite « par texte libre et filtres facultatifs » précise la fonction exacte.
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?
La description donne explicitement le cas d'usage : « À utiliser lorsque vous n'avez PAS d'identifiant de produit », avec un exemple concret. Elle indique aussi quand ne pas l'utiliser (absence d'ID), mais ne nomme pas directement les alternatives comme get_product, ce qui empêche la note maximale.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get_productlookup_catalogsearch_catalog
Add one secure layer between your agents and this server.