Browse category

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

Annotations already declare read-only, idempotent, non-destructive, open-world behavior, so the safety profile is covered. The description adds return-content context (ancestors plus sub-categories plus top products), which is valuable given there is no output schema, but it says nothing about pagination over the 10-default limit or what happens at tree edges.

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, front-loaded with what the caller gets, followed by the routing rule. No filler and nothing redundant.

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 does carry the burden of describing results and does so briefly (parents, sub-categories, top products). Given six parameters that include filtering and pagination, an agent still has to infer how results are paged and ordered, keeping this short of full coverage.

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?

At 67% schema coverage, the description adds essentially no meaning for page, limit, sort, brand, or max_price — all are left to the schema. The only parameter-adjacent info is the parenthetical showing that tb_search also accepts a category argument, which is a cross-tool hint rather than semantics for this tool's inputs.

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?

"A category page: its parents, sub-categories and top products" states the resource and enumerates what comes back, and "Use to walk the category tree" gives the agent an unambiguous job for the tool. It is clearly separable from tb_search, though it stops short of a verb-first statement of the operation.

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?

Explicitly routes text queries elsewhere: "For text search in a category use tb_search(category=)" names the sibling and the condition that selects it. No guidance is given on when to prefer other category-adjacent siblings (tb_filters, tb_brands), but the main disambiguation is handled.

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