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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered by structured data. The description adds genuinely new behavioral context: customer review text is immutable and only the owner's reply can be changed, which tells the agent the boundary of what any downstream write tool can touch.

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?

Three tight sentences with the resource described first, filters second, and the immutability constraint last. No filler, though the immutability note would read more clearly if it pointed at which sibling to use for replying.

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 does the necessary work of stating that each review carries the owner reply and any drafted reply, so the agent knows what comes back. Missing only pagination/limit behavior and whether results are ordered or capped at 100.

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 40%, with limit, max_rating, and unanswered undocumented in the schema. The description supplies the accepted value shape for two of them (unanswered=true, max_rating=3), but never states what max_rating means as a bound (at most this rating) and says nothing about limit or its 1-100 range.

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 first sentence names a specific resource and scope: Google reviews for the site's location, including the owner reply and any drafted reply. An agent can distinguish this from mutating siblings like draft_google_review_reply or sync_google_reviews, though neither alternative is named explicitly.

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?

"Filter unanswered=true or max_rating=3 for reviews needing attention" gives a concrete usage pattern for triage-style calls, which is real guidance. However, it never says when to prefer this over list_review_queue or when to call sync_google_reviews first to refresh data, so sibling selection is left to inference.

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