chewy_brands

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

With no annotations, the description carries the full behavioral burden and does so thoroughly. It discloses pagination ('Returns one page'), scale ('roughly 7,600 brands'), exact return fields, case-insensitive exact-match semantics with a concrete example, and even the fact that facet_id is not accepted by the filter parameter. This goes well beyond a simple list operation.

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 sentence carries unique information: scope, return fields, differentiation from chewy_facets, exact-match behavior, and downstream filter usage. The first sentence front-loads the core purpose, and nothing is redundant or filler. Though longer than average, the density justifies the length.

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?

The description is complete for an agent to call the tool correctly: it explains the catalog scope, pagination, the name lookup semantics, and the relationship to facet ids. Even without an output schema, it lists the returned fields (id, name, description, image, parent-catalog group, child brands), so the agent knows what to expect. No missing guidance is apparent.

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?

The schema already documents all three parameters at 100% coverage, so the baseline is 3. The description adds valuable semantics beyond the schema: the name parameter is an exact match, not a search, is case-insensitive, and gives the 'Purina' vs 'purina pro' example. It also explains how the name parameter relates to filtering in other tools, which is extra context the schema alone does not provide.

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?

The description opens with a specific verb and resource: 'List Chewy's brand directory.' It clearly states this is the whole catalog of roughly 7,600 brands and explicitly contrasts itself with chewy_facets, which only covers brands in one category's listing. This distinguishes it well from its siblings without needing to inspect anything else.

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?

The description explicitly names chewy_facets as the alternative and tells the agent when this tool is the right choice ('This is the whole catalog of brands, unlike chewy_facets'). It also gives actionable routing guidance for downstream filtering: pass the brand's NAME to chewy_category or chewy_search as filter=brand_facet:<name>. This is explicit when/alternative usage context.

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