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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety bar is low. The description still earns credit for disclosing the hard 95-day inclusive limit, the off-by-one trap (94-day delta), and the analytic constraint not to average ratios like ACOS/ROAS but recompute from summed base metrics.

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 95-day / non-overlapping-window rule is restated three separate times ('each request may contain at most 95 calendar days', 'MCP reporting and workflow metric date ranges... at most 95 calendar days per range', 'For longer read-only reports, split into non-overlapping windows'), which crowds out front-loaded guidance on what the reports contain and when to use them.

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?

Date-window constraints are covered exhaustively and an output schema exists, so return values need not be explained. But for a 9-parameter, 4-report-type analytics tool that sits beside several other sales/order/traffic queries, it says nothing about what distinguishes summary vs dailySummary vs sku output or why an agent would choose it over its siblings.

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 100%, so the schema already documents every parameter, including startDate/endDate semantics and the limit cap. The description adds only the ratio-recomputation caveat relevant to reportType choice, not meaning for skus, storeIds, sortBy, or offset; 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?

States a specific verb and resource and enumerates the four report types that map to reportType. However, it never distinguishes itself from close siblings like query_sales_orders, query_sales_traffic, or query_profit, so an agent must infer which 'sales' tool to pick.

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?

Nearly all guidance is about date-window math rather than tool selection; the one implicit routing cue is the note that keyword ranking trends have separate limits (pointing at query_keyword_rank_trends). No explicit statement of when to prefer this over query_sales_orders or query_sales_traffic, and no prerequisites or exclusions for its own use.

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