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

Annotations declare readOnlyHint=true, so safety is already covered, but the description adds genuine behavioral context: rank direction (lower = better), the `scope` field on catalogue-wide results, the parentAsins+groupBy childAsin interaction, and the important caveat that an empty result means 'no filter match' rather than 'no BSR data'. It does not cover pagination behavior or the shape of series rows, which is the main residual gap.

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?

Front-loaded with the core claim and the sibling exclusion, and nearly every clause carries operational value. Slightly overstuffed: the design-rationale aside '(a plain average would sever it)' and the emphasis casing ('CORRECT', 'ONE call', 'ALL') are rhetorical rather than informative.

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?

With 15 parameters and no output schema, the description carries the return-value burden well: it explains what 'latest' returns (last observed rank plus period-average main/sub category ranks, optional baseline delta), that rows come back per product, that catalogue mode exposes a `scope` field, and how errors surface on empty filters. Nothing critical is missing for correct invocation.

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 already 80%, yet the description still adds non-obvious semantics the schema cannot express: the product list must match groupBy (skus/childAsins/parentAsins) and be passed in ONE call, and parentAsins combined with groupBy childAsin returns the parents' children. It also restates limit's default (50) and the baseline pairing. tags/accounts/marketplaces add nothing beyond the schema.

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+resource (BSR for the seller's products) and immediately differentiates from the nearest sibling: 'query_metrics does NOT serve BSR.' Also pins the scope (per-marketplace category/rank pair) rather than a blended average.

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?

Explicit routing instructions — use THIS for any BSR question, query_metrics is not an alternative — plus concrete mode selection: granularity='latest' for a point-in-time read, a time grain for a series, and product-list vs catalogue-bestsellers depending on whether skus/childAsins/parentAsins are supplied. It even warns against the wrong invocation pattern (never loop one call per ASIN).

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