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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds useful scope limits (purchase cost and margin not returned; extra data like other-unit prices and shop texts only when few items match). It is somewhat verbose about what is returned but gives no pagination, truncation-with-limit, or response-shape guidance. Good added context, but not exceptional beyond the strong annotation baseline.

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?

Front-loaded with the core purpose and return values, then examples, then batching guidance, then the alternative tool. It is longer than necessary — the quoted Ukrainian/English query phrases and the parenthetical shop-texts detail add bulk — but every sentence still carries usable routing or expectation 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?

There is no output schema, so the description carries the return-value burden and does so thoroughly: price per unit, currency, tax inclusion, stock on hand, description, and conditional extra data. It also states the exclusions (cost, margin), which prevents an agent from expecting margin data.

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 67%, the description meaningfully adds that 'query' accepts a short name stem, item number or barcode, and that 'queries' is for several names/spellings/products in one call. It does not explain the 'limit' parameter's effect (max 20) or what an empty query plus limit yields, so a little schema-covered ground is left to the schema alone.

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 (find products/goods/services in the catalog by name, SKU or barcode) and names exactly what comes back (sale price, currency, tax inclusion, stock on hand, description). It is immediately distinguishable from erp_product_set_price, which is explicitly called out as the price-changing tool.

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 explicit when-to-use examples in natural query form, tells the agent to batch multiple names/spellings into one 'queries' call rather than repeated calls, and routes price changes to erp_product_set_price. Multi-match behavior (list prices or ask which one) is also specified, leaving little to inference.

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