ozon_analytics

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

No annotations are provided, so the description carries the full disclosure burden. It does add valuable behavioral context: which metric families are deprecated by Ozon and which ones actually work. However, it does not disclose response shape, pagination behavior (despite a limit parameter), or how metrics are aggregated per SKU, leaving meaningful gaps for an unannotated 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?

Three short sentences, each earning its place: core purpose, deprecation warning, and sibling routing. The critical information is front-loaded ('Analytics by SKU' and the working trade metrics) with no filler or 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?

The highest-risk failure modes are addressed: the deprecated metric set is explicitly called out, and the search-position use case is routed to the correct sibling. But with no output schema and no annotations, an agent still lacks expectations for return values, date format requirements, and whether metrics are raw counts or sums — gaps the description should have covered given the absent structured metadata.

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?

With schema coverage at 40%, only metrics and dimensions have schema descriptions. The description adds real value by warning that session_view, hits_view, and position_category are deprecated — metrics an agent might plausibly guess at since they don't appear in the schema's allowed list. However, date_from/date_to format, range semantics, and limit behavior are undocumented in both the schema and the description, so it only partially compensates for the coverage gap.

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 'Analytics by SKU' and enumerates the working metric set (revenue, ordered_units, delivered_units, returns, cancellations), making the resource and scope clear. It also differentiates itself from the sibling ozon_product_queries by stating that tool handles search positions. It stops short of 5 only because the verb is implicit ('Analytics' rather than 'Get/Retrieve'), but the intent is 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?

Provides an explicit exclusion and alternative: 'For search positions use ozon_product_queries (аналитика).' It also instructs the agent not to use deprecated funnel metrics through the deprecation warning. Lacks explicit contrast with other analytics siblings like ozon_analytics_stocks or ozon_product_rating_by_sku, so it falls just short of comprehensive routing guidance.

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