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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile needs no repetition. The description adds real behavioural context beyond that: the exact payload of the returned card, the fuzzy-match fallback returning nearest names when a name is missing, and the fact that the hub forwards the query to the Moja Serowarnia server (an external source). It does not mention result limits or whether the shop offers are exhaustive.

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 purpose is front-loaded in the first clause and the fallback rule comes before the source/attribution tag at the end. The middle enumeration is a long run-on list of returned fields, but every item is informative content rather than filler; the bracketed module note is compact and useful.

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 one-parameter lookup tool with no output schema, the description does the heavy lifting by enumerating exactly what the response contains and by describing the nearest-name fallback. What is missing is only the relationship to adjacent tools (search and substitutes), which would matter for an agent choosing between them, plus any note on how many shop offers are returned.

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 the single 'nazwa' parameter is already documented as a trade name from packaging or from szukaj_kultur results. The description reinforces this with concrete trade-name examples and explains the not-found behaviour, but it adds no format constraints (spelling, case sensitivity, partial-name matching) beyond what the schema states, so the baseline of 3 applies.

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 verb and resource — it fetches the full card of one bacterial culture by trade name — and enumerates the card's contents (species composition, application, temperature, dosage, manufacturer, strain proportions, shop offers with price per litre and link). The word 'jednej' (a single culture) implicitly separates it from the search-type siblings, but no sibling such as serowarnia_szukaj_kultur or serowarnia_zamienniki is named in the description itself to sharpen the boundary.

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?

Usage is implied rather than stated: the agent gathers that this is the tool to call once it has a trade name (the examples 'Choozit MA 4001', 'ALPHA 10', 'DELTA 2' show the expected input form). The fallback sentence ('Gdy nazwy nie ma, zwraca najbliższe nazwy') hints at when to fall back to a search tool but never names it or states an explicit when-not-to-use rule, e.g. for comparing substitutes.

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