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

With no annotations, the description carries the full burden and does useful work: it discloses the exact response shape including that prices are VAT-inclusive, which matters for downstream interpretation. It does not address auth/access requirements, pagination behavior, or empty-result behavior, but for a read-only public product search those are lower-stakes gaps.

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?

Three sentences, zero filler. It front-loads what the tool does, then the return fields, then how to steer the search, so an agent can act after the first line.

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?

Five optional parameters, no output schema and no annotations – the description compensates by listing return fields and giving keyword syntax, so nothing essential for correct invocation is missing. Language, paging and result limits are all covered by the schema descriptions rather than duplicated here.

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 every parameter is already documented, and the baseline is 3. The description does add a little beyond the schema – the 1–3 keyword convention, keyword examples, and the pairing of category_id with an omitted query – but the schema itself already states query is optional when category_id is given.

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 ("Search products by keywords and/or category") and even enumerates the return fields (name, price with VAT, availability, URL, image). It implies the boundary against list_categories by offering a category_id browse path, but it never names get_product or list_categories, so the sibling differentiation is inferred rather than stated.

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?

It gives concrete use conditions: 1–3 keywords in the shop language with example keyword types (product name, size, category word), and it explains the browse-only path (category_id with no query). What's missing is any explicit exclusion such as "do not use to fetch a single known product – use get_product instead", which keeps it 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.