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

Annotations already declare destructiveHint=true and readOnlyHint=false, so safety is covered. The description adds real context beyond that by enumerating what is destroyed — the agent, its mailbox, and all its API keys — which is exactly the blast-radius information an agent needs before calling a destructive tool.

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?

One sentence, front-loaded with the permanence warning and the cascade, with zero filler. Nothing could be removed without losing information.

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 zero-parameter destructive tool with no output schema and annotations carrying the safety profile, the description covers the essentials: permanence and blast radius. It omits behavior on failure (e.g., unknown/already-deleted agent) and whether deletion is immediate or asynchronous, which would round it out.

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?

Zero parameters, so the baseline is 4; there is no parameter surface the description needs to explain, and the implicit 'this agent' target matches the parameterless schema.

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?

A specific verb ('Permanently deletes') plus a specific resource ('this agent') with the cascade scope spelled out (mailbox and API keys), which implicitly sets it apart from mailbox_delete and apikey_revoke. It stops short of naming those alternatives explicitly, so the distinction must be inferred.

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?

The word 'Permanently' signals this is the nuclear option, and the cascade disclosure implies you should only use it for full teardown. But there is no explicit when-to-use / when-not-to-use guidance and no pointer to narrower siblings like apikey_revoke or mailbox_delete for partial cleanup.

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