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

With no annotations, the description carries the full burden and does real work: it discloses permanence, revocation of the relay address, and the downstream effect that dealer emails are silently dropped. What's missing is whether the thread and its history become unrecoverable, and whether any confirmation or permission is required.

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?

A single front-loaded sentence with the destructive effect stated first and the consequence second. The 'one-click privacy kill-switch' framing is slightly promotional but does convey that no setup is needed.

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, irreversible action with no annotations and no output schema, the description explains the effect well but leaves recovery, thread-history fate, and any required confirmation unstated — gaps an agent would want closed before invoking.

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%, with both thread_id and reason documented including an example reason, so the schema does the heavy lifting. The description adds no parameter-level detail beyond that, which is the baseline-3 case.

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 concrete verb+resource pair: permanently closes a shielded deal thread and revokes its proxy relay email. That is far more specific than the name alone and clearly separates it from read-oriented siblings like get_deal_thread, though it never names a sibling to contrast with explicitly.

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?

'One-click privacy kill-switch' implies the intent (cut off dealer contact) but never states when to use it versus alternatives such as accept_deal_and_reveal or send_counter_offer, nor any precondition or confirmation requirement. Usage is inferable but not guided.

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