Supprimer une prestation/livraison

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

Even though annotations already carry destructiveHint=true and readOnlyHint=false, the description adds substantial value: irreversibility with no API-side recycle bin, the conditional elicitation/confirmation flow (refusal yields deleted:false + reason), and the permission-check pointer. It details the return shape including the refusal case. No contradiction with annotations.

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?

Well-structured with a bolded 'Quand' section, 'Plutôt que' alternative section, and bullet points that front-load the critical safety constraints before the return format. Every sentence earns its place for a destructive operation; the length is justified by the gravity of the action.

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?

Comprehensive for a destructive mutation tool: covers when to use, the safer alternative, irreversibility, permission pre-check, the elicitation confirmation flow with its exact return behavior, and output shape. Even though an output schema exists (making the return description partially redundant), the refusal semantics and confirmation logic would be invisible without the description.

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% for the single `id` parameter, so the schema fully documents it (numeric pattern, unique identifier description). The description adds the operational context of verifying the ID via boond_deliveries_get before deleting, which is useful but does not add format/syntax detail beyond the schema. Baseline 3 for full coverage is appropriate.

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 opens with a specific verb+resource: 'Supprime définitivement un(e) livraison (CRA)' (permanently deletes a delivery/CRA). It clearly distinguishes this from siblings like boond_deliveries_update (state change) and boond_deliveries_create, making the destructive purpose 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?

Exceptional routing guidance: it states exactly when to use ('uniquement sur demande explicite de l'utilisateur, et après avoir vérifié l'ID avec boond_deliveries_get'), and explicitly names the alternative (boond_deliveries_update) with the rationale that non-destructive state changes are 'presque toujours l'intention réelle'. Also references boond_rights_get for permission pre-checks.

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