Найти товар

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

Annotations already indicate readOnly, openWorld, idempotent, and non-destructive behavior. The description adds non-obvious behavioral details beyond those annotations: name searches are paginated and limited, results may be partial, a nextCursor is returned, and multiple candidates are possible. This is exactly the kind of runtime behavior that helps an agent avoid incorrect silent selection.

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 three short sentences with no filler: first sentence states the purpose and accepted inputs, second sentence describes pagination behavior, third sentence gives an actionable warning. It is front-loaded with the most important information and every sentence earns its place.

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 six parameters, a nested cursor object, and no output schema, the description covers the core search semantics and pagination caveat, but it leaves important context unstated: what partial results look like, how to provide cursor, brand, or subjectId, and how nextCursor should be fed back in. It is adequate for a first invocation but not fully complete.

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 0%, so the description must carry the burden of explaining parameters. It does clarify that query can be an nmId, seller article, barcode, or name, and it hints at cursor semantics via 'nextCursor.' However, brand, subjectId, maxPages, and the cursor object structure are left unexplained, so the description only partially compensates for the missing schema 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 states a specific action ('поиск своего товара' - search for your product) against a clear resource, and enumerates the search keys: nmId, seller article, barcode, or name. This differentiates it from siblings like wb_read or wb_product_profile, which are about reading or viewing profiles rather than finding a product by multiple lookup methods.

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 gives clear usage context: use this tool to find a product by identifier or name, and it explains that name searches scan only limited pages. It also provides a concrete decision rule: do not silently pick a product when multiple candidates exist. It does not explicitly name sibling tools or state when not to use it, but the guidance is clear enough.

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