Delete

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

Annotations already declare destructiveHint=true, but the description adds real value beyond them: it discloses that the deletion is permanent ('définitivement'), that it cascades to chunks, and that a summary of what was removed is returned. It does not mention permission or auth requirements, so not a full 5.

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?

Three short sentences, each load-bearing: what is deleted, what is returned, and the invocation constraint. The restriction is front-loaded after the core purpose with no filler.

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?

An output schema exists so return detail is covered, annotations cover the destructive profile, and the description adds cascade behavior plus the consent constraint. An agent has everything needed to decide and call correctly.

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 doc_id parameter, and the description adds no meaning beyond it (no format hints, no alternative identification schemes). Baseline 3 is appropriate when the schema fully documents the only 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?

States a specific verb (supprime) and resource (document), plus the cascade scope (et ses chunks), which distinguishes it from siblings like update or add_text. The 'définitivement' qualifier makes the permanence unmistakable.

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 an explicit, unusually strict invocation condition: only when the user explicitly requests it in the current message, never on the agent's own initiative. This is exactly the when/when-not guidance that prevents accidental destructive calls.

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