WB Catalog Categories

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, and the description correctly doesn't restate them. Instead it discloses the genuinely non-obvious behavior: the live menu is ~800 KB so responses are always a bounded slice, which tells the agent to page through the tree rather than expect the full catalog in one call. It also documents that each node carries WB's own shard and query selectors, plus points to the guide resource for error codes, though it never says what an unmatched root returns.

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 short blocks ordered what → when → behavioral constraint → reference pointer, with the most decision-relevant facts front-loaded. The humidifier example illustrates why a query-less browse is needed rather than padding the text, and every sentence carries information.

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 and the description correctly does not enumerate return fields, instead deferring to `guide://wb/wb_categories` for the field list and error codes. Given a 2-parameter, no-required-input tool with full annotation coverage, the discovery→expand workflow plus the size warning is everything an agent needs to call it 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 baseline is 3; the description earns an extra point by adding procedural meaning to `root` — the 'top'-first expansion strategy is what actually makes the parameter usable against an 800 KB tree. It adds nothing about `max_depth` values, leaving the depth/cost tradeoff to the schema 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?

States a specific verb and resource ("Browse the Wildberries catalog tree") and immediately distinguishes it from wb_search by noting that search requires a query string while this tool works without one. The one gap is that it never names wb_category_products, the obvious next step after obtaining a node's shard/query selectors, so the boundary with a nearby sibling is left implicit.

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?

Gives an explicit when-to-use rule with rationale — discover what exists before searching, because a shopper's question may not contain a search term. It also prescribes an iteration strategy ("start at 'top', then expand the branch you care about"). What's missing is the counterpart routing: an explicit statement that once a node is chosen, wb_category_products should be called to pull the feed.

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