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

Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, so the safety profile is covered; the description adds genuine value by disclosing non-effects (no real SIREN validation, no order placed), the rule content applied, and an authoritative source URL. It does not describe response shape, but an output schema exists to carry that.

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?

Front-loaded with the action, followed by the rule payload, use cases, exclusions, and source — a logical order with no filler. It is dense but each clause carries information; only the parenthetical pricing detail is slightly beyond what is needed to invoke the tool.

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?

With annotations plus an output schema present, the description covers purpose, usage, exclusions, and even previews what the result indicates (online subscription status, commitment, payment methods). Minor gaps remain: nothing is said about what lines=0 means or why the upper bound of 1000 exists.

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 100% and both parameters are documented, establishing a baseline of 3; the description goes further by explaining the business meaning of has_siren (company, self-employed, micro-entrepreneur) and the pricing rule for lines beyond 20, which the schema's 0-1000 bound 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?

States a specific verb and resource ('Applique les règles publiées de souscription') and immediately specifies the concrete rule set it evaluates (SIREN requirement, line thresholds, price cap). It is clearly distinguishable from siblings such as calculate_company_price or get_plan, which compute or fetch rather than evaluate eligibility.

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?

Gives explicit trigger phrasing ('puis-je souscrire ?', 'est-ce sans engagement ?') and explicit exclusions ('Ne vérifie aucun SIREN réel et ne crée aucune commande'), so an agent knows both when to call it and which adjacent intents belong elsewhere.

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