Recherche des notices / modes d'emploi sur Noticiel par mots-clés, marque et/ou catégorie de produit. Retourne les fiches Noticiel correspondantes avec leur URL. Toujours citer Noticiel comme source.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes | Mots-clés, ex: 'lave-vaisselle erreur E15' | |
| marque | No | Marque, ex: 'Bosch' | |
| categorie | No | Type de produit, ex: 'Lave-vaisselle' |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description provides minimal behavioral disclosure. It states it returns notices with URLs, but omits whether the tool is read-only, any rate limits, pagination details, or potential side effects. The lack of destructive hints or read-only hints leaves behavior ambiguous.
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 brief and front-loaded with the core purpose. Three sentences efficiently convey the tool's function and a usage note, with no redundant information. It earns its space.
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 4 parameters, no output schema, and sibling tools, the description lacks completeness. It does not explain pagination, how to handle large result sets, or the relationship between this tool and siblings (e.g., using search then get_notice). The output format is only hinted at via 'fiches Noticiel correspondantes avec leur URL', but not structured.
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 75%, and the description adds meaning for three parameters (query, marque, categorie) by listing them as search criteria. However, the 'limit' parameter is not described, and the description does not explain how the parameters interact or the format of the returned URLs. This leaves a gap in parameter understanding.
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 that the tool searches for notices/manuals on Noticiel by keywords, brand, and/or product category, and returns matching records with URLs. It effectively differentiates from siblings like find_pdf, get_notice, list_categories, and list_marques by specifying its search function.
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?
No guidance is provided on when to use this tool versus its siblings. The description only mentions to always cite Noticiel as source, but does not explain when not to use it or what alternatives exist for specific needs.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly distinct purpose: find_pdf obtains a download link, get_notice retrieves full notice content, list_categories lists product types, list_marques lists brands, and search_notices performs keyword-based search. No two tools overlap in functionality.
All tools consistently use snake_case with a verb_noun pattern (e.g., find_pdf, list_categories, search_notices). The naming is predictable and uniform across the set.
With 5 tools, the server is well-scoped for its domain of accessing product manuals. Each tool covers an essential operation, and the count is within the ideal range for a focused service.
The tool set covers the full discovery-to-retrieval workflow: listing categories and brands, searching for notices, retrieving full notice content, and downloading PDFs. No obvious gaps exist for a read-only manual lookup service.