list_evenementsLes visites guidées, nocturnes et ouvertures exceptionnelles à venir, relues chaque nuit sur l'agenda du ministère de la Culture. Chaque événement porte l'URL de sa page.
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | ||
| limite | No | 24 par défaut. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden for behavioral context. It usefully discloses the data source, the nightly update cycle, and the fact that each event carries a page URL. However, it does not state whether the operation is read-only or describe any side effects, pagination, or response-level behavior beyond the URL detail.
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 short and to the point, with two sentences that each add value: one defines the content and source, the other highlights the included URL. The structure is efficient, though the first sentence is a noun phrase rather than an action-oriented statement, and there is minor overlap with the title.
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 simple listing tool with two optional parameters, the description provides enough to understand the general output and freshness, but it stops short of describing the actual return structure beyond the URL, or how language and limit parameters affect the response. Given no output schema or annotations, a bit more return-value detail would make it complete.
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 50%: 'limite' has a description, 'lang' has only an enum. The description adds no parameter-level context, such as how 'lang' affects results or how 'limite' interacts with the default. Since the tool description does not compensate for the half-covered schema, parameter semantics are underspecified.
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 tool's purpose is clear: it provides upcoming events at castles, specifically guided tours, night events, and exceptional openings, sourced from the Ministry of Culture's agenda. The domain is distinct from siblings like get_chateau and list_itineraires, though the description itself lacks an explicit verb and relies on the tool name and title for part of the meaning.
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 usage for upcoming events by emphasizing 'à venir' and the nightly refresh, but it gives no explicit guidance about when to choose this tool over list_itineraires, get_chateau, or search_chateaux. There are no exclusion criteria or alternative routing hints.
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 targets a different resource: one château detail, one château search, one event list, one itinerary list. The 'list_evenements' vs 'list_itineraires' pair could seem similar at first, but the descriptions clearly separate time-bound events from computed routes.
All tools use a consistent snake_case verb_noun pattern: get_chateau, list_evenements, list_itineraires, search_chateaux. Mixed singular/plural in French nouns is natural and does not affect consistency.
Four tools is a focused, intentional set for a read-only encyclopedia server. It falls comfortably within the 3–15 tool range and each tool provides a unique capability without redundancy.
The domain of château information is covered by search + detail retrieval, with events and itineraries extending the surface nicely. There is no way to fetch a single event or itinerary by ID or filter events by château, but these are minor workarounds for agents.