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

Goes well beyond the destructive/non-idempotent hints: it explains that the change is replayed through the same checks and into the same change log, that successive calls chain backwards, that undos are not themselves reversible, and that restoring a pass-visible detail pushes the restored line to every registered phone. That is exactly the side-effect detail 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?

Purpose is front-loaded in the first clause and nearly every sentence carries new constraints. It is dense and semicolon-chained, though, so some clauses ('restoring the value the detail had before it, through the same checks and into the same change log') read as run-on rather than crisp.

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?

With no output schema, the description still enumerates the return payload (the detail, before/after values, a human-readable sentence, and `passNotice` when passes are on), plus auth needs and error behavior. Nothing material is missing for correct 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 already documents both id and name forms, so the schema carries the semantics. The description only reinforces the token requirement and names `eventIdOrName` without adding format or resolution rules, which is the baseline-3 situation.

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 precise verb and scope: 'Reverses the caller's own most recent change to a wedding or other personal event they host.' This clearly separates it from the forward-mutation sibling event_change_detail and from site_undo_publish (different resource), so an agent can pick it without opening the 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 strong exclusion conditions: only hosts, only their own changes, an undo is not itself reversed, and each further call walks back the next older change. The NOTHING_TO_UNDO case is spelled out. It stops short of naming a sibling alternative (e.g. use event_change_detail to make a new change instead), so it lands just below the top.

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