Supprimer une facture fournisseur

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

Goes well beyond annotations: states irreversibility, no recycle bin, conditional confirmation behavior based on elicitation capability, and return semantics with deleted:false on refusal. DestructiveHint=true annotations are reinforced with concrete consequences.

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?

Every sentence earns its place: purpose, trigger conditions, alternative, prerequisite check, danger warning, confirmation behavior, and return format. The bulleted structure makes the key safety points scannable without padding.

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 single-parameter delete tool, the description covers all necessary context: when to call, what to check before, what the consequences are, how the confirmation flow works, and what the response contains. Nothing an agent needs to invoke it safely 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?

Schema covers the id parameter 100% with type, pattern and description. The description adds the procedural note to verify the ID with a get call, but that's usage guidance rather than parameter semantics. Baseline 3 is appropriate since schema already fully documents the parameter.

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 'Supprime définitivement un(e) facture fournisseur de BoondManager', which is a specific verb+resource+scope. It clearly distinguishes the tool from the update sibling by explicitly naming boond_provider_invoices_update as the alternative for non-destructive state changes.

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 when-to-use guidance: only on explicit user request and after verifying the ID with boond_provider_invoices_get. It also names the preferred alternative (update) with rationale, and references boond_rights_get for authorization checks. This fully routes the agent.

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