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

Annotations already declare readOnly/openWorld=false/idempotent/non-destructive, so the safety profile is covered; the description still adds real value by stating money is returned in the profile's native currency and that attribution_link reads enrolment status rather than enrolling. Return-field disclosure compensates for the absent output schema.

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?

Every clause carries information and the highest-value mode (health_check) is front-loaded, with no filler sentences. The heavy semicolon-and-parenthesis packing makes it denser than ideal for one-pass reading, which keeps it off a 5.

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 20-parameter, single-required-param tool with no output schema, the description covers what each report returns, its currency, and its side-effect boundaries. Remaining gaps are minor: pagination semantics and the default/max row behavior are left entirely to the schema.

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 95%, so the baseline is 3 and the schema already documents per-report applicability for asin, limit, format, dates and filters. The description adds only a little beyond that, chiefly what omission of asin means for attribution_link; it says nothing extra about target, columns or sortBy defaults beyond what the schema states.

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?

Each of the four report modes is described with a specific verb/resource pair and concrete payload (e.g. product_performance returns 'spend, sales, ACOS, ROAS, CTR, CPC, conversion rate'), which clearly separates it from siblings like query or run_query. It falls short of 5 only because there is no single lead sentence stating what the tool itself is, leaving the agent to infer the dispatch pattern from the 'report:' prefixes.

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 context is given per mode with in-line questions ('what needs attention?', 'missed opportunities') and an explicit negative constraint on attribution_link ('does not enrol'). No alternatives among siblings are named and no when-not-to-use is stated, so it stops short of the top band.

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