Rend les 11 catégories et leurs sous-catégories, avec le nombre de fiches de chacune. À appeler AVANT chercher quand on ne sait pas quel terme employer : les sous-catégories sont un vocabulaire fermé, deviner un nom rend une liste vide.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden. It discloses that the tool returns the category/subcategory structure with counts and explains the closed-vocabulary behavior. It does not describe the exact output format, but for a zero-parameter catalogue tool this is sufficient.
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?
Two concise, information-dense sentences. The first front-loads the return value; the second provides usage context with a concrete warning. 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?
For a zero-parameter catalogue tool with no output schema, the description covers what it returns, how many categories, what accompanies them, and the strategic context relative to 'chercher'. Nothing essential is missing.
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?
The tool has zero parameters and schema description coverage is 100%, so there is nothing for the description to add. The baseline of 4 applies.
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 states a specific verb 'Rend' and a precise resource: the 11 categories and their sub-categories with record counts. It also relates to the sibling 'chercher', which distinguishes its purpose as a listing/lookup 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?
Explicitly directs the agent to call this tool BEFORE 'chercher' when uncertain about terminology, and warns that sub-categories are a closed vocabulary and guessing yields an empty list. This is clear when-to-use guidance and includes the consequence of misuse.
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 distinct resource or action: commune code lookup, search, category vocabulary, association registry, and volunteer missions. There is mild overlap between `chercher` and `associations` for finding associations, and between `associations` and `missions` in associative life, but the descriptions draw clear boundaries.
Names are short, lowercase, and readable, with most being French nouns (`associations`, `catalogue`, `commune`, `missions`). However, `chercher` is an infinitive verb, breaking the otherwise mostly nominal pattern; there is no consistent verb_noun or action_noun scheme.
Five tools is well-scoped for a read-only French local-life lookup server. Each tool earns its place: a code resolver, a general search, a category helper, an association registry query, and a volunteer-missions feed.
The set covers the main workflows implied by the server's purpose: `chercher` handles local searches, `commune` prepares INSEE codes, `catalogue` guides vocabulary, `associations` answers association questions, and `missions` covers volunteering. Minor gaps exist, such as no detailed view for a single result and no reverse postal-code lookup, but core use cases are supported.