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

Annotations only supply the read-only/idempotent safety profile, so the description carries the domain behavior and does it well: newest-first ordering, inlined published reply text, Google's moderation lifecycle (approved/pending/rejected), and the non-obvious coupling that a rejected reply yields has_reply=false with reply_policy_violation explaining why. That is real context an agent could not infer from the schema or annotations.

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 sentences, front-loaded with purpose and filters before the denser moderation caveat. The final sentence packs a long parenthetical but every clause carries distinct information, with no filler.

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 work of describing return contents (reviews plus inlined reply text, reply_state, has_reply, reply_policy_violation), which is the important part. It omits pagination mechanics (limit max 50, offset) that a listing tool of this shape would benefit from mentioning.

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 only 43%, and the description compensates for most of the gap by naming the four filter families that map to location_id, rating_min/rating_max, unanswered_only and since_days, clarifying that the two rating parameters form a range and that unanswered_only excludes Google-rejected replies. It says nothing about limit/offset, so it does not fully cover all seven parameters.

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 and resource ('List Google reviews for the org') plus ordering ('newest first') and an inlining behavior, so the agent knows exactly what comes back. It is implicitly distinct from get_review_stats and get_usage, but it never names a sibling to contrast against, which keeps it just short of 5.

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?

The description enumerates the available filters (location, star range, replied/unreplied, trailing day window), which implies when the tool is the right entry point, and its closing note points toward drafting a new reply after a rejection. It gives no explicit when-not guidance or routing to siblings like get_review_stats or list_locations.

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