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

Annotations already establish readOnly, idempotent, non-destructive, and closed-world behavior, so the safety profile needs no restatement. The description adds genuine context: the metrics returned, per-location plus org-total scoping, and the trailing-window semantics with a 30-day default. It does not mention auth requirements, rate limits, or how zero-activity locations are handled.

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?

A single front-loaded sentence that leads with the resource and scope, then enumerates metrics. Dense but no filler; the metric list and the window default are the only load-bearing clauses.

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, describing the returned metrics is exactly the right call, and annotations already cover the safety contract. For a two-parameter, read-only stats tool this is close to complete, missing only edge-case behavior (empty locations, window exceeding data history) and response shape granularity.

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 50%: location_id is documented in the schema as 'omit for all locations' and days carries only a default and bounds. The description restates the 30-day default and clarifies that the window is trailing and that omission yields org totals, but it does not explain the 1-365 bounds, aggregation behavior, or what happens when days is set below the review window. Partial compensation, not full.

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?

Names a specific verb and resource ('Review stats') and enumerates the exact metrics returned (counts, average rating, star breakdown, unanswered count, trailing-window activity), which implicitly separates it from list_reviews. It never names a sibling explicitly, so the distinction from get_usage or list_reviews is inferred rather than stated.

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?

Usage is implied by the name and metric list, but there is no explicit guidance on when to call this versus list_reviews (raw records) or get_usage, and no prerequisites or exclusions are given. An agent can infer the aggregate-vs-list split, but nothing is spelled out.

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