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

Annotations already declare destructive/non-idempotent/open-world, and the description goes further with genuinely non-derivable behavior: attributes are only restored 'where Google allows', booking-link changes and photo deletions are permanently irreversible, and owner consent is required. That is exactly the extra context annotations cannot supply.

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?

Front-loaded with the core action, then three tight sentences covering scope, exclusions, and the consent requirement. No filler or redundancy despite the enumeration.

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, non-idempotent mutation with no output schema, the description covers the action, the accepted input source, partial-success semantics, irreversible cases, and a consent prerequisite. Nothing an agent needs to invoke it safely is missing.

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?

Single parameter with 100% schema description coverage, so the schema already explains that change_id comes from a propose_ tool or my_changes. The description does not restate or enrich the parameter, which is acceptable at this coverage level but adds no marginal value.

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 specific verb+resource ('Reverse a change') with a precise scope qualifier ('that was published from Claude') and the intended effect ('restoring what the profile had before'). The 'published' scoping implicitly separates it from proposal-side siblings like discard_change and propose_* tools.

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 real when-it-works and when-it-does-not guidance: enumerates what can be reversed (descriptions, hours, contact details, categories, services, review replies, posts, added photos) and explicitly excludes booking-link changes and photo deletions. It also adds a consent prerequisite ('Ask the owner first'). It stops short of naming the sibling alternative (e.g., discard_change for un-published proposals).

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