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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, so the safety profile is covered. The description adds valuable behavioral context: it reveals that the tool computes the cheapest delivery with its date, price after coupons, and price range over variants—behaviors not inferable from the schema alone. No contradiction with annotations.

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 a single, well-structured sentence that front-loads the primary purpose and output attributes, followed by a concise exclusion note. Every phrase contributes value; no redundancy or fluff. It is efficient and easy to parse.

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?

The tool is moderately complex (comparison with up to 10 items, multiple output dimensions, city-based pricing). The description covers the key output elements and explicitly notes what is NOT included (seller details). Since an output schema exists, return format is not required. It does not mention error handling or edge cases, but the essential information for calling the tool correctly is present.

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% for both parameters (city and items), so the baseline is 3. The description adds meaning by clarifying that the comparison uses the 'pre-selected variant' and details coupon pricing and delivery selection, which enriches understanding of how the 'items' parameter is interpreted. This goes beyond the schema's generic 'ids or URLs' description.

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 clearly states the tool's function: comparing up to 10 products side-by-side, listing specific attributes (price, price range, coupon price, delivery, rating, etc.). It also explicitly contrasts with get_product for seller details, distinguishing it from a sibling. The verb 'compare' and resource 'products' are precise and unambiguous.

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 an explicit exclusion: seller details and characteristics are only in get_product, so an agent knows not to use this tool for that. It implicitly indicates usage for multi-product comparison via 'up to 10 items' and the side-by-side framing, but does not explicitly state when to prefer it over search_products or get_reviews. Clear enough for typical cases.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds context like 'live' (real-time data) and the effect of quantity on coupons, but no additional behavioral traits (e.g., rate limits, error handling) are disclosed. The bar is lower due to annotations, and the description adds some value without contradicting them.

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 dense but well-structured: a lead sentence capturing the essence, followed by a comma-separated list of returned items. It is front-loaded with the core purpose and each clause earns its place. While long, the complexity of the return data justifies the detail, and it avoids redundancy.

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?

Given the tool's complexity (6 parameters, output schema present, annotations provided), the description covers the return content thoroughly, listing all major data categories. It doesn't address error cases or usage prerequisites, but the required item_id is self-evident and the output schema likely details return structure. The 'live' and 'priced for one variant' framing add important context.

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 parameters are already documented. The tool description adds semantic value by explaining how parameters affect the output: quantity influences coupon calculations ('what the coupons really give at `quantity`'), city affects the delivery quote, and sku_id selects the variant to price. This goes beyond the schema's isolated parameter descriptions.

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 clearly states the tool's function: 'Full live card for one item, priced for one variant.' It specifies the verb (returns) and resource (product card) and enumerates a comprehensive set of returned data. The purpose is unmistakable and distinct from siblings like search_products (search) and get_reviews (reviews).

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 implies usage: when you need a complete product card for a single item. However, it does not explicitly mention alternatives or when not to use it, nor does it contrast with sibling tools. The detailed output list makes it obvious this is the single-item detail tool, but no explicit guidance is given.

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

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

The description goes well beyond the readOnly/idempotent annotations by disclosing real behavioral quirks: texts are machine-translated into Russian with the original preserved in original_text, the rating is aggregated across all variants, and aspect tags are optional. It also flags the review-composition details that affect how an agent interprets results.

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 front-loaded: the first sentence states the core capability, and the second efficiently lists return fields in a scannable colon-list format. Every sentence adds either scope or behavioral detail, with no filler or repetition of schema content.

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 tool with 10 parameters, an output schema, and read-only/idempotent annotations, the description is complete enough for an agent to call it correctly. It explains the key output semantics, while the schema covers all input parameters and the output schema covers return structure, leaving no critical gap.

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%, and the input schema already explains each parameter thoroughly, including sort semantics, item_id URL formats, source_id auto-correction, and aspect-tag examples. The main description adds only a general mention of sorting/filters and optional aspect tags, so it does not materially improve parameter understanding beyond the schema.

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 names a specific resource ('buyer reviews') and a clear action ('get'), then details exactly what is returned: review fields, item rating, star split, and optional aspect tags. It is immediately distinguishable from the sibling tools, which target search, single-product details, and comparison rather than reviews.

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 intended use is implied clearly by 'Buyer reviews with real pagination, sorting and filters' and the item_id requirement, but there is no explicit statement of when to use this tool versus a sibling like get_product. The description also mentions the item rating, which could overlap with get_product, so exclusions or routing guidance would help.

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

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.