Ozon Catalog Search

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

Annotations already cover read-only, open-world, idempotent, and non-destructive behavior, so the bar is lower, yet the description still adds real operational context: a two-tier fetch strategy (curl_cffi then CDP fallback), the shape of each returned item, and the critical semantic that count=0 is a warning rather than a failure. The parser-internals line about tileGridDesktop-* widgets and mainState atoms is more implementation trivia than actionable behavior, keeping it from a 5.

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 purpose and return shape are front-loaded in the first two lines, followed by the important zero-result caveat and a pointer to the guide resource. The middle line about Nov 2026 tileGridDesktop widgets is dense jargon that consumes space without helping an agent decide or invoke, which is the only real waste.

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 the description needn't enumerate return fields, and it correctly limits itself to a summary plus the non-obvious empty-result semantics and a deep-link to guide://ozon/ozon_search for full fields and error codes. For a two-parameter search tool this is close to complete; only the routing versus ozon_card/ozon_reviews is unaddressed.

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% with only two parameters (query, page), and the schema already documents the Russian-language requirement and the 1..10 page range. The description adds nothing about query syntax, transliteration, or paging limits beyond the schema, 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 Ozon catalog") and names the return fields (sku/title/price/rating), so the agent knows this is a keyword-search tool rather than a product-detail lookup. It does not explicitly distinguish itself from siblings like ozon_card or ozon_reviews, so it falls short of a 5.

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?

Usage is only implied by the tool name and the sibling set; nothing states when to prefer this over ozon_card (single item) or ozon_reviews (reviews). The one genuinely useful usage rule it does give is that zero parsed items is not an error but surfaces a no_items warning with meta.healthy=false, which tells the agent how to interpret an empty result rather than when to call the tool.

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