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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds the irreversible consequence ('There is no undo') and, more importantly, the required confirm/warn/confirm workflow, which is behavioral detail not present in any structured field.

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 ordered by importance: consequence first, eligibility second, invocation sequence third. Every sentence changes agent behavior; none is 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?

For a destructive, single-param mutation with no output schema and annotations that already cover the safety profile, the description supplies everything the agent needs: irreversibility, permission condition, and the exact call sequence.

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% and the single parameter is fully documented in the schema itself ('true only after the person has confirmed, in their own words'). The description restates the same gating condition rather than adding new semantics such as what a false/omitted value returns, so the baseline 3 applies.

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 and resource and qualifies scope ('the person's account and everything in it'), so an agent knows exactly what is destroyed. It does not, however, distinguish itself from relevant siblings such as export_my_data or update_profile, which is the one thing keeping this from a 5.

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 explicit when-to-use ('Only use it when the person asks to leave') and a precise two-step invocation protocol: call without confirm to retrieve and read out the warning, then call again with confirm=true only after a clear yes. Nothing is left to inference.

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