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

With no annotations, the description carries the full behavioral burden. It usefully discloses the matching semantics for attributes (exact, case-insensitive, keys are the store's own spec attributes) and that prices are in the store's currency. It is silent on pagination, sort behavior, and what the response contains, leaving real gaps for a 10-param tool.

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 compact sentences, front-loaded with the core purpose and semantics, with zero filler. Dense but every clause (matching semantics, currency, example, composability) earns its place.

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?

For a 10-parameter, annotation-free tool with a nested object and no output schema, the description covers the filters but omits pagination/sort behavior and parameter-level detail for several fields. It is adequate to justify the core filtering use case but not complete for the tool's full surface.

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 only 30% schema coverage the description must compensate, and it does for the hardest parameter: it explains that 'attributes' takes store-specific key:value specs that match exactly and case-insensitively, and it gives price_min/price_max examples in the store's currency. It leaves page, page_size, sort, and fulfilment undescribed, so the compensation is partial but meaningful.

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 action (filtering products) and the two dimensions it filters on (attribute values and/or price range), with a concrete example. It does not, however, explicitly distinguish itself from the likely-overlapping siblings 'search' or 'browse', leaving that differentiation to inference.

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 closing clause 'Combine with a category, brand and in-stock' gives implied usage guidance on how the filters compose, and 'see any product's attributes' points the agent to a discovery path. There is no explicit when-to-use-this-vs-'search'/'browse' guidance or exclusion, so usage remains inferred.

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