Supprimer une référence (expérience pro)

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

Annotations declare destructiveHint=true and the description reinforces this with an explicit irreversibility warning and the read-modify-write mechanism. It also discloses the error case (untraceable referenceId returns isError with the present IDs list) and the return shape. Fully consistent with annotations and adds meaningful behavioral context beyond them.

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 labeled sections (Quand / Plutôt que / Returns) and front-loaded core action and caution. Every sentence earns its place — mechanism, warning, usage, alternative, return behavior — with no filler. Slightly long for a delete operation but the length is justified.

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 destructive 2-parameter tool with no output schema, the description is comprehensive: read-modify-write mechanism, irreversibility warning, when-to-use guidance, alternative tool, return format, and error behavior. Nothing an agent needs to call 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 description coverage is 100% — both resourceId and referenceId are already documented in the schema. The description reiterates the referenceId error behavior but adds little semantic value beyond the schema's own parameter descriptions, so the baseline 3 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?

States a precise verb (Supprime), the exact entity (une référence / expérience professionnelle) and its container (le DT d'une ressource), and distinguishes itself from the update sibling by explicitly naming boond_resources_reference_update as the alternative. An agent can select this tool correctly without opening any schema.

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?

Contains an explicit 'Quand' section giving the trigger condition (remove an experience entered by mistake, upon explicit user request) and an explicit 'Plutôt que' section routing to boond_resources_reference_update for corrections rather than destruction. No inference required.

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