search_products

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states that it searches and applies filters, but it does not reveal any behavioral traits such as pagination (limit/offset meaning), error handling, authentication requirements, or the shape of the response. It does not mention whether results are store-scoped (though 'in a store' implies store_id). Beyond that, there is no information about rate limits, sorting semantics, or how promotions are filtered. This is a significant gap for a search operation with no annotation support.

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?

The description is a single, concise sentence that front-loads the primary action ('Search products') and lists the filter dimensions. It has no repetition or fluff. It is appropriately sized for the tool's complexity, though it could be slightly longer to include critical parameter context. For a tool with 9 parameters, it may be too terse, but the structure itself is clean and to the point.

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?

Given the complexity (9 parameters, no annotations, no output schema), the description is clearly incomplete. It does not explain the two required parameters (store_id and query) beyond a loose implication of 'in a store'. It does not mention limit/offset pagination, enum choices for sort, or how filters interact. The description provides only the high-level purpose and filter names, leaving an agent without enough context to correctly invoke the tool without further schema inspection.

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 0%, so the description must compensate. It names filter categories (price, brand, promotion, sorting) which loosely map to parameters like price_min/price_max, brand, promo_only, and sort, but it does not explain individual parameters. It omits the meaning of required fields query and store_id (though 'in a store' hints store_id). It does not clarify the enum values for sort, the semantics of limit/offset, or the default behavior. The description provides only a high-level overview, which is insufficient for the 9 parameters.

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 states a clear verb ('Search') and resource ('products in a store') and enumerates the filter dimensions (price, brand, promotion, sorting). It is specific enough to suggest this is a filtered search tool, though it does not explicitly differentiate from sibling tools like find_products or list_category_products, which might also involve searching/filtering products. The mention of 'apply ... filters' gives a distinct purpose.

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 implies usage: use this when you need to search products with filters. However, it does not provide explicit guidance on when to choose this versus siblings like find_products, list_category_products, or get_product_info. There are no exclusions or alternatives mentioned. The context of filters gives some direction but the usage is only implicit, not explicit.

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