Creer un paiement

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

Annotations already indicate non-idempotent, non-readOnly, destructive=false. The description adds critical behavioral details: the API requires a `purchase` relation (without it, call is refused) and that writes are not idempotent (two identical calls create two payments). This goes beyond annotations by explaining the side effects and constraints. It could mention more about potential side effects but 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?

The description is concise and well-structured, with a clear intro, a 'Quand' section, a 'Plutôt que' section, bullet points for API requirements and idempotency, and a brief note on returns. Each sentence adds value, no redundancy. It's efficiently front-loaded with the purpose and immediately covers usage guidance.

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 the tool complexity (13 params, 1 required) and that there is no output schema, the description provides essential context: the necessity of `purchaseId`, non-idempotency, and a brief return mention. It doesn't detail all parameter behaviors (e.g., required fields for amount), but the schema covers those descriptions. The description is adequate for an experienced agent, though a note about minimum required fields could improve it.

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 100%, so baseline is 3. The description adds extra context: it explains that `amount` maps to `amountExcludingTax`, `paymentDate` maps to `date`, and `note` maps to `informationComments`. It also highlights the critical requirement for `purchaseId` to link to an existing purchase, which is vital for correct use. This goes beyond the schema by clarifying mapping and the mandatory relationship.

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 ('Enregistre') and resource ('un paiement / règlement fournisseur adossé à un achat'), which is clear. It distinguishes itself from sibling `boond_purchases_create` by explicitly noting it is for payments attached to existing purchases, not for creating purchases themselves. However, it doesn't explicitly compare to `boond_payments_search` or `boond_payments_get`, but the primary purpose is unambiguous.

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?

Provides explicit 'Quand' (when to use) and 'Plutôt que' (instead of) guidance, naming the alternative `boond_purchases_create` and the condition for choosing it. This helps the agent select the correct tool. It also clearly states that a payment cannot be orphaned, preventing misuse.

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