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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered; the description adds real behavioral context beyond that: default non-zero filtering, the freshness caveat that the most recent ~3 days may be incomplete, and the explicit list of excluded metrics. It stops short of describing pagination or row shape, though the schema and output schema cover those.

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?

Three sentences, each front-loaded with the highest-value fact: what is returned and the default filter, the freshness caveat and toggle, then the exclusions and alternatives. No filler or restatement of the tool name.

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 tool with full schema coverage and an output schema, the description supplies everything an agent still needs: the attribution grain, default filter semantics, data-freshness limits, and which siblings cover the metrics this tool omits.

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 parameters such as limit, offset, sort_by and non_zero_only are already fully documented in the schema. The description restates the non_zero_only default behavior but adds no syntax or semantics beyond what structured fields provide; baseline 3 is appropriate.

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 (returns purchase attribution rows) plus the exact grain: advertised ASIN to purchased ASIN, campaign/ad group, sales, orders, units. It also names the sibling tools that cover the metrics it lacks (get_product_performance, get_sales_and_traffic, get_tacos), so an agent can distinguish it without opening any 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?

Gives explicit when-to-use (halo/cross-sell attribution patterns), the default filtering behavior, and the condition that flips it (set non_zero_only=false to include zero-attribution rows). It also states when NOT to use it by naming three alternative tools for spend/clicks/ACOS/total sales.

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