bonnes_pratiques

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

With no annotations, the description carries the full burden and does so well: it states that the tool contains no tenant data, is public rules only, is a GET request, and that server-side guardrails remain authoritative. This makes side effects and data scope clear.

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 relatively compact and front-loaded, but the use of all-caps and repeated emphasis ('WHEN', 'FREE', 'NO tenant data') adds slight noise. Still, each sentence contributes useful usage or safety information.

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 one-parameter tool with no output schema, the description provides everything needed: endpoint, query parameter, domains, response shape, data scope, and usage priority. No critical context 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 single optional 'domaine' parameter is described in both the input schema and the tool description, including a concrete query example. The enum values are listed and the default behavior when omitted is explicitly stated.

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 identifies the tool as a versioned playbook of best practices for MCP/API agents, naming the resource, endpoint, and return structure. It distinguishes itself from sibling tools by emphasizing its 'first call' meta-role and its domain-filterable rules.

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 explicitly instructs the agent to call it first upon discovering the server and again if cached instructions may be stale. It also notes that no API key/units are required and that server-side guardrails remain authoritative, giving clear usage boundaries.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.