search_products

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive behavior. The description adds meaningful behavioral context beyond these: it clarifies that the tool mimics real-site behavior, explains that price sorting uses AliExpress's own price field which can cause shown prices to fall outside the requested window, and warns that listing_sku_id may pre-select a different variant than what's shown. This significantly enhances an agent's understanding of edge cases without contradicting any annotation.

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 compact and information-dense, with every sentence serving a purpose. It front-loads the core purpose, then systematically lists output fields, explains pagination fields, and closes with a crucial caveat about price sorting. There is no redundancy or filler, making it easy for an agent to parse quickly.

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 search tool with an output schema and seven parameters, the description is remarkably complete. It explains the meaning of key output fields (listing price, coupon price, rating, orders, delivery estimate, flags), notes that review counts are absent, clarifies pagination via total_found and has_more, and references get_product for pricing the correct variant. This covers all essential aspects an agent needs to use the tool correctly.

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 the schema already documents all seven parameters with descriptions. The tool description adds value by explaining the price-window caveat (relevant to interpreting price_min/price_max) and the pagination ordering (already in the schema's page parameter). However, it doesn't introduce any new parameter meaning beyond what the schema provides; it only contextualizes existing definitions. Thus a baseline 3 is appropriate.

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 'Search aliexpress.ru like the site does: real pages, sorting, a price window,' which precisely states the tool's purpose and its key capabilities. It goes on to detail the per-item output fields and explicitly references the sibling tool get_product when discussing listing_sku_id, distinguishing this search tool from that product-detail tool. Though it doesn't contrast with get_reviews or compare_products, the purpose is unmistakable and specific.

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 provides clear operational context: it explains how to use listing_sku_id with get_product, notes that review counts are not in listings (implying the use of get_reviews), and describes pagination ordering. However, it does not explicitly state 'use this tool when you need to find products' or give direct exclusions against alternatives. The guidance is implicit rather than explicit, 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.