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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the exact result fields returned (name, type, application, temperature, shop, price, price per litre of milk, culture card link) and the matching rule that every query word must appear in name, application, type or composition. Rate limits, ranking details and pagination beyond the limit parameter are not discussed.

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 user-facing question, then the search behavior, then the return shape, then the matching rule — a sensible order. The cheese/yogurt/kefir/twaróg list is repeated verbatim in the first two sentences, which is the only real waste. Length is justified by a six-parameter tool with several filter axes.

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?

With no output schema, the description compensates by enumerating every returned field, so the agent knows exactly what a hit contains. Combined with the AND-matching rule, the filter semantics and the note that the hub forwards the query to the module's server, nothing needed to call this tool correctly is missing.

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 the enum values, limits and defaults are already documented and baseline would be 3. The description earns an extra point by explaining the semantics the schema cannot: the query is tokenised and each word must appear in name, application, type or composition, and the temperature filter returns cultures whose range covers the given value. The sort option's meaning (cheapest per litre of milk) is also restated, which overlaps slightly with 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?

Names a specific action and resource: searching bacterial cultures by cheese name or application, with filters for type, working temperature and shop, plus a price-per-litre field. The scope (cheese, yogurt, kefir, twaróg) is concrete enough that an agent can distinguish it from a recipe or ingredient search. It stops short of naming the sibling lookup tool for a single culture, so sibling differentiation 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 clear triggering contexts: when the question is 'which culture for this cheese/yogurt/kefir/twaróg' or 'where to buy it', and illustrates query values such as "camembert", "twaróg", "jogurt grecki", "mozzarella". It also mentions the hub routes the question to the module's own server, which tells the agent this is a delegated knowledge lookup. There are no explicit exclusions or 'use X instead' statements, so guidance is strong but not exhaustive.

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