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

Annotations already cover the safety profile (readOnlyHint, openWorldHint=false), yet the description still adds real behavioral context: results are LIVE catalog data including price-from and availability, and the important caveat that with forma/linia the price and availability describe only the matching variant, not the whole product. That variant-scoping warning is exactly the kind of non-obvious behavior an agent needs and cannot get from annotations or schema.

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 kept to four sentences, all relevant. Minor redundancy: 'Returns LIVE catalog data (price from, availability)' and 'Prices and availability come from the live catalog' restate the same fact, costing a bit of tightness.

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, so return values need not be described, and the description correctly focuses on matching scope, liveness of data, and variant-level pricing. Gaps remain around result limits/pagination and whether results are ranked, but for a read-only search tool with a fully documented schema this is close to 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 coverage is 100%, so baseline is 3, but the description genuinely enriches two parameters: it explains that 'fraza' matches name, Latin name, or common alias (broader than the schema's 'reishi'/'sleep' examples) and that an empty string returns everything, plus it clarifies the forma/linia semantics. The remaining filters (cel, sort, kategoria, rodzaj) are left to the schema.

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 ('Searches the Aloha Fungi product catalog') and defines the match scope ('name, Latin name, or common alias'), which tells an agent exactly what is being searched. It stops short of naming how it differs from siblings like show_product or recommend_products, so a 4 rather than a 5.

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 one useful usage fact — an empty 'fraza' returns the full catalog — which is really schema/usage behavior. It gives no explicit when-to-use guidance and never says when to prefer show_product, polec_produkty, or search_knowledge over this tool, leaving selection to inference from the names.

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