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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false and openWorldHint=false, so safety and side effects need no restatement. The description instead adds two things annotations cannot: results are timestamped with a source, and — critically — "Brak komunikatu nie znaczy, że szlak jest bezpieczny," which tells the agent how to interpret an empty result rather than presenting it as a safety clearance.

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?

Three sentences, each earning its place: what is returned and from where, when to call it, and the safety caveat on empty results. The most decision-relevant material (scope and sources) is front-loaded.

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 read-only, single-optional-enum lookup with no output schema, the description is nearly sufficient: it conveys the data sources, the presence of a status date and source per item, and the empty-result caveat. The only gap is the unaddressed default behavior of kraj and any hint about result volume or freshness window.

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?

Coverage is 0% for the single optional parameter kraj, and the description never mentions it, so the schema's enum values (Polska/Słowacja) do the work. The enum is self-explanatory, but the description leaves open what happens when kraj is omitted (both countries returned?) — a real ambiguity for a filter parameter that is not required.

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 concrete resource (current park notices on closed trails and obstacles) and enumerates the actual sources covered — live TPN, seasonal TANAP/TPN closures, Slovak HZS entries — plus the fact that each item carries a status date and source. That is far more specific than the sibling tools (szukaj_tras, trasa, wyznacz_trase), which all deal with route search/planning, so an agent can separate this from them by subject alone.

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?

"Użyj, gdy ktoś pyta, czy szlak jest otwarty albo co jest zamknięte" gives an explicit triggering question type, which is exactly the routing signal an agent needs. It stops short of 5 because it names no alternative tool or negative case (e.g., what to use when the user wants route options rather than closure status).

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