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

The annotations already flag destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is known. The description still adds real value by enumerating the specific artifacts destroyed and by stating permanence ('for good') and the 30-day automatic-retention baseline. It stops short of saying whether a confirmation step or particular permissions are 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?

Two sentences, front-loaded with the destructive consequence before the usage note. Every clause carries information: what is erased, how permanently, when to call it, and the automatic alternative. No filler or restatement of the tool name.

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 one-parameter destructive tool with full annotation coverage and a declared output schema, the description supplies what annotations cannot: the extent of data loss and the 30-day auto-deletion policy. The main residual gap is error and permission behavior on an invalid or foreign reviewId, which is a minor omission rather than a blocking one.

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?

There is a single required parameter, reviewId, with 0% schema description coverage, and the description says nothing about it. The schema's regex pattern does convey the expected ID format, which narrows the gap, but the agent gets no guidance on where a reviewId comes from or what happens if it belongs to another user. Adequate, not enriching.

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?

The description uses a concrete verb of removal ('Erase') plus the resource ('a review') and enumerates exactly what is removed: the document, its text, the answers and the report. It is unambiguous about the operation and even about its scope. It doesn't explicitly name a sibling tool, but no sibling performs deletion, so differentiation is implicit rather than stated.

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?

It gives an explicit trigger ('Use it when the user asks') and an alternative path in the same breath: reviews are erased automatically 30 days after they start. That tells the agent both when to invoke it and when doing nothing is acceptable. It doesn't cover prerequisites such as ownership or confirmation, which keeps it short of a 5.

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