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

Annotations already cover readOnlyHint=true and destructiveHint=false; the description adds genuine methodology beyond that: the metrics are estimates weighted by buy-box share and restricted to ASINs the operator 'wins', and it surfaces observed buybox days as an empirical counterpart to the estimates. This clarifies subtle scoring behavior an agent could not infer from the annotations or 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?

Four dense sentences with the core purpose and default sort front-loaded. The quoted example queries are slightly redundant with the opening sentence, but they serve as practical query-matching anchors for the agent, and the sibling pointer is a single efficient clause. No filler.

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 no output schema, the description correctly carries the burden of specifying return fields (est_units_30d, est_revenue_30d, ASIN count, observed buybox days), which is essential. Gaps remain: pagination/limit behavior, the distinction between brand vs brand_contains, and filter semantics are unaddressed. For the primary brand drill-down use case it is complete, but the richness of 14 params leaves room.

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 only 29% (4 of 14 params documented), so the description must compensate — but 10 filter params (limit, brand_contains, min/max_asin_count, min/max_est_units_30d, min/max_est_revenue_30d, min/max_observed_buybox_days) receive no meaning in either source. The description does clarify the buy-box-weighted semantics behind est_units_30d/est_revenue_30d, which indirectly informs the min/max filters, but that is partial compensation at best.

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 ('Show'), resource ('brands an operator sells'), and scope ('for each brand the operator carries'), with the default ranking basis explicit ('ranked by ESTIMATED 30-day sales'). It distinguishes itself from the sibling operator_brands_by_competition (sales vs fewest sellers) and from operator_top_asins (brand-level vs ASIN-level granularity) without ambiguity.

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?

Provides explicit, quoted when-to-use triggers ('what brands does this seller sell the most of', 'top brands for operator X', 'which brands make this seller the most money', 'any brand-level operator drill-down by sales') and names the exact alternative with its selection condition ('For brand competition (fewest sellers) instead of sales, use operator_brands_by_competition'). Nothing is left to inference.

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