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

Annotations already declare destructiveHint=true and idempotentHint=true, so the bar is lower, but the description still adds substantial context: the key is invalidated immediately, the number can never be used again, and the operation requires explicit human instruction. This characterizes the destruction concretely rather than restating the annotation flag.

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?

Two sentences, both front-loaded and zero-waste: the consequence of the call comes first, followed by the permission gate and the alternative. Nothing is repeated from the annotations or schema.

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 2-parameter destructive action whose safety profile and parameters are already carried by annotations and a fully described schema, the description supplies exactly what structured fields cannot: irreversibility, the human-authorization requirement, and the migration path. No output schema exists, and none of the omitted return-format detail matters for an irreversible teardown.

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%, so both the secret and the confirm flag are already documented in the schema, including the ls_ prefix and the "Must be true" constraint. The description's only parameter-relevant contribution is an implicit tie between the human-approval rule and the confirm flag, not new syntax or format detail.

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 ("Cut this app off from your line for good") plus the concrete effect: the key stops working and the number becomes unusable. It explicitly distinguishes itself from the sibling move_line, so an agent can route correctly without opening either 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?

Gives an explicit gating condition ("Use it ONLY when your human asks you directly"), a motivating example (suspected leak), and names the alternative for the adjacent case ("To keep the number in another app, use move_line instead"). Both when and when-not are covered.

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