Browse a category or brand

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is fully covered structurally. The description adds the precondition that at least one of category/brand/price bound must be supplied, but says nothing about result format, pagination limits, or empty-result behavior beyond what the input schema already documents (e.g. in_stock_only's stale-price caveat).

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 sentences plus a compact example, front-loaded on the purpose with the constraint and usage context trailing. Nothing is padded, though the example largely restates what the first sentence already conveys.

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 an eight-parameter, annotation-rich, read-only browse tool with no output schema, the description covers purpose, entry-point workflow and the one non-obvious precondition. It omits anything about the shape of returned product data, but with rich schema documentation and the query-building rule stated, an agent has enough to call it correctly.

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?

With 100% schema description coverage the baseline is 3, but the description adds a genuine cross-parameter rule absent from the schema: at least one of category, brand, min_price or max_price must be given (no parameter is marked required). The inline example also shows how category, brand and sort compose, which the schema's per-field descriptions do not.

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 with scope modifiers: 'List products of a category and/or brand, optionally in a price range, sorted by price or rating.' That is clear enough to act on, but it never differentiates itself from bn_search or bn_find_cheapest, so the agent must infer that this is slug/pivot browsing rather than free-text search or the dedicated cheapest lookup.

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 a concrete workflow position ('Use after bn_categories / bn_brands to see what a section holds') plus an operational rule ('Give at least one of category, brand or a price bound') and a worked example. It stops short of saying when NOT to use it, e.g. that free-text queries belong to bn_search or that bn_find_cheapest already covers the single-cheapest case.

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