search_products

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

Annotations cover the safety profile (readOnly, idempotent, openWorld, non-destructive), and the description adds substantial semantics beyond them: prices are for the listed variant, guest vs signed-in price kinds, `below_price_window`, the 2000-result ceiling, the category-redirect case, and the caveat that promo codes are a condition rather than a subtraction. This is exactly the behavioral context an agent cannot get from structured fields.

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?

It is front-loaded with the one-line purpose, then a compact per-item field list and behavioral caveats. Dense but every clause carries information; the return-field enumeration is somewhat verbose given an output schema exists, which keeps it from a 5.

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?

An output schema exists, so fully documenting return fields is not strictly required, yet the description includes it plus the redirect and result-cap edge cases, making the definition self-sufficient for correct invocation. The only gap is the absence of guidance against the other browsing/search siblings.

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 100%, so every parameter (city, page, sort, limit, query, price bounds) is already documented, including the 24-per-page cap and the guest-price basis for sort and price filters. The description largely restates these semantics rather than adding new parameter-level detail, so the baseline 3 applies.

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 goldapple.ru like the site does'), then scopes it to real pages, sorting, and a guest-price window. It differentiates from siblings by naming get_product as the confirmation step and by explaining the category-page redirect behaviour that separates it from browse_category.

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 clear context for use (replicate the site's search, guest vs signed-in pricing) and explicitly names the follow-up tool: 'Confirm finalists with get_product.' It does not, however, state when NOT to use it versus browse_category or compare_products, so it falls short of a full when/when-not statement.

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