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

Annotations already establish readOnly/idempotent/non-destructive, and the description adds real behavioral context beyond them: the most-recently-updated ordering, why unanswered reviews sort to the end, the unpublished_estimate discrepancy versus Google's count, and the review_not_replyable error on reply attempts.

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?

Long but front-loaded and information-dense; the core purpose and the reply sibling come first, then paging and edge cases. Every sentence states a distinct, actionable fact, though it is approaching the upper bound of acceptable length.

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 5-param read tool with annotations and an output schema, the description covers ordering, paging, filtering modes, and the unpublished/unreplyable edge case. An agent has everything needed to select modes and avoid futile reply attempts.

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 description coverage is 0%, so the description carries the load and does well for summary_only, only_unanswered, and offset+limit semantics (including next_offset). It does not explain the required `location` parameter's expected format, which is the one remaining gap.

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 ('Lists a business location's Google reviews') and enumerates the returned fields. It also names the sibling gbp_reply_review, so an agent can distinguish read from write without opening either 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?

Explicitly prescribes when to use each mode: summary_only for counts, only_unanswered for reviews needing a reply, offset+limit for paging (with next_offset), and says to prefer only_unanswered over paging. It also warns not to retry unpublished reviews, naming gbp_reply_review as the alternative.

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