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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered. The description adds the reporting grain and metric scope but says nothing about freshness/latency of the data, row limits, or pagination behavior beyond what the schema documents. With annotations carrying the safety burden, this meets the lower bar but adds only modest extra context.

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?

Two tight sentences: the positive scope comes first, the exclusions and routing second. Every clause earns its place, with no restating of the name or title.

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 13-parameter read-only reporting tool with a full output schema, the description supplies the scope, grain, and routing needed to select and call it correctly. Minor gap: no note on default date window behavior at the description level, though the schema and output schema cover the rest.

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% – every one of the 13 parameters, including the date defaults, LIKE-match filters, and diagnostics flag, is documented in the schema. The description adds no parameter-level detail (e.g., how order_name interacts with the grain), so the 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 (reporting on) and resource (Amazon DSP Reporting v3 performance) plus the grain (order, line item, creative) and the metrics returned (spend, sales, ROAS, viewability, video completion). This distinguishes it cleanly from sibling ad-reporting tools like get_sb_campaign_performance or get_sponsored_ads_report.

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 covers both when to use (DSP performance by order/line item/creative) and when not to use it, calling out Sponsored Products/Brands/Display, search terms, and seller account sales as out of scope, then routing to 'the matching ads or sales tool'. Nothing is left to inference about tool selection.

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