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

Consistent with readOnlyHint=true and destructiveHint=false, and it goes well beyond the annotations: the 95-inclusive-day cap, the exact split algorithm (endDate = startDate + 94, next startDate = previous endDate + 1), the rule that ratios like ACOS/ROAS must be recomputed from summed base metrics rather than averaged, and that comparison ranges are limited independently. The only weakness is that some disclosed limits (keyword ranking DAILY/RAW caps, campaign scheduling dates) belong to sibling tools and dilute the disclosure.

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?

The purpose is front-loaded in sentence one and the chunking algorithm is actionable, but the middle section is bloated with rules for tools other than this one — keyword ranking DAILY/RAW interval limits and campaign scheduling exclusions — which consume roughly a third of the text without affecting how this tool is called.

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 10-parameter read tool with full schema coverage, an output schema, and read-only annotations, the description covers the one non-obvious operational constraint (date-window size and splitting) thoroughly. It is short only on how reportType selects between summary and row-level output, which is the main remaining ambiguity for an agent.

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 100%, so the schema already documents every parameter including the yyyy-MM-dd format and the 95-day inclusive range — the description largely restates this. It adds no meaning for reportType, whose six enum values (store, dailyStore, asin, parentAsin, dailyAsin, dailyParentAsin) determine the shape of the response and are never explained. Baseline 3 applies.

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 verb (Returns) and a specific resource (sales traffic summaries / paginated sales traffic metrics), scoped to ASIN or parent ASIN, one store, and a date range. That is enough to distinguish it from write-side siblings, but it never distinguishes it from the closest read siblings query_sales and query_sales_orders, which an agent must choose between.

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?

It gives real when/when-not guidance for the date dimension: split read-only reports into non-overlapping windows, but do not auto-split write plans or metric-based selectors — ask the user for a supported window. It gives no guidance at all on when to pick this tool over query_sales or query_sales_orders, so tool-selection guidance is only implied.

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