Search products

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

Annotations only state readOnly/openWorld; the description adds the meaningful behavior: the result partitions into bestMatch vs choices, with an explicit action rule for each, and that bestMatch is usually a previously purchased item. It omits what happens on zero results or any pagination/rate considerations.

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 tight sentences: purpose, input constraint, then the two result cases in order of likelihood, then the flag definition. No filler and the most decision-relevant content is front-loaded.

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 carries the return-value burden and does so by explaining bestMatch, choices, and boughtBefore. The empty-result case is left implicit, which is the main remaining gap for an open-world search.

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 coverage is 100%, so baseline is 3, but the description adds real semantics beyond the schema: the query must be Dutch and a short product name rather than a free-form phrase. That measurably improves match quality for the caller.

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 ('Search the Picnic supermarket for a product') plus the downstream payoff ('get its id for add_to_cart'), which distinguishes it from get_product, which takes an id rather than a query. An agent can pick this tool without opening the schema.

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 explicit branching instructions for the two result shapes: use bestMatch directly, but ask the user when choices comes back. Also constrains input ('Dutch, short product name'). It does not name sibling alternatives such as get_product or get_favorites, so it falls short of a 5.

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