Browse Ozon category

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

The description discloses a major non-obvious behavior: Ozon matches numeric id only, so a guessed slug can open a different category, and a text-prefix mismatch causes an error. This goes far beyond the readOnly/openWorld/idempotent annotations by explaining data provenance, failure modes, and the need to copy slugs from trusted sources. It also notes that filters{} behave like ozon_search, connecting behavior across tools.

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?

Four tight sentences plus one capital-letter warning carry purpose, usage, return summary, a critical caveat, and a cross-tool reference. The warning about slug provenance is front-loaded and earns its length; there is no filler or repetition. Despite 19 parameters, the prose stays compact and scannable.

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 19-parameter tool with no output schema, the description gives enough context to select it correctly and avoid the main footgun (slug provenance). The compact/rich behavior and filter syntax are already described in the schema, so the description doesn't need to repeat them. The main gap is that return shape and pagination details are only implied, leaving some uncertainty about output expectations.

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 only 42%, so the description must compensate. It does address the two most delicate parameters: category (exact slug, numeric-id matching, error on mismatch) and filters (same syntax as ozon_search), while also highlighting priceMax as a primary browsing axis. But 16 other parameters—sort, compact/rich, seller/delivery flags, minReviews, etc.—are left to bare names or schema descriptions, leaving a significant gap for an agent.

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 'Products inside a category without text search,' a specific verb+resource pair that makes the tool's function unmistakable. It contrasts with text-search tools (notably ozon_search) and names return artifacts (products, breadcrumbs, top brands). This clearly distinguishes it from the sibling tool set.

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 explicitly states the intended scenario: 'Use for browsing a department with priceMax/filters.' It also teaches where to source the required slug (ozon_list_categories, ozon_search_filters, or real ozon.ru link), which is a crucial prerequisite. However, it never explicitly says 'for text queries use ozon_search' or spells out when-not-to-use, relying on the phrase 'without text search' to imply the boundary.

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