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

With no annotations supplied, the description carries the full behavioral burden. It does disclose the blast radius ("everything stored about the client") and a safety gate (explicit client request plus confirm=true), but says nothing about irreversibility, whether deletion is permanent or recoverable, or any auth/permission requirement — critical omissions for a destructive operation.

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 short sentences, zero filler, with the destructive scope stated first and the invocation condition immediately after. Nothing could be removed without losing meaning.

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-in-spirit tool with no annotations and no output schema, the definition covers scope and the confirmation gate but leaves the agent guessing about permanence, recovery options, and side effects on related data. Adequate to avoid misuse, but not complete enough for confident invocation.

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 self-documenting ("Must be true"). The description still adds value by framing confirm as a deliberate safety gate tied to an explicit client request rather than a mere boolean toggle.

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?

"Erase everything stored about the client" gives a specific verb (erase) and a clear scope (all client data), which no sibling tool overlaps with. It stops short of naming what 'everything' concretely includes (records, files, history), so it is clear but not maximally precise.

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?

"Only call when the client explicitly asks" is an explicit precondition that gates invocation, which is strong for a destructive tool. It does not name alternatives (e.g., a data-export or partial-deletion tool), but none exist among the siblings, so the omission costs little.

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