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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavior: the exact return keys (results/count/next_after/total, with total only on page 1) and the quota rule "Jedna strona wyników = 1 z puli", which is a cost signal not present anywhere else.

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 tight sentences: filter scope first, then return shape and pagination, then the routing hint. No filler, and each clause carries actionable information for a 31-parameter tool.

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?

Given no output schema, the description takes on the burden of explaining return values and does so explicitly, including the page-1-only total field and the cursor mechanism. For a 31-param tool it cannot cover every parameter, but the filter taxonomy plus sibling pointer covers the main decision burden; ordering of results and default limit behavior (only in schema) remain implicit.

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 71% schema coverage the baseline is already decent, and the description adds group-level meaning by enumerating which filter families are supported and tying them to the export endpoint, implying identical filter semantics. It does not clarify the less obvious params (status, pkd_glowne, category slug, nºwcode ranges) beyond what the schema says, so it stops short of full compensation.

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 resource and output type: KRS numbers of companies matching filters, with the filter set enumerated (region, PKD, forma, kapitał, ocena, VAT, przetargi, KRZ, revenue/profit/valuation, metryki). It explicitly contrasts with the sibling tool firma, which returns company details, and anchors the filter semantics to the export endpoint /pobierz-dane.

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?

Routes the agent clearly for the detail case ("Dane konkretnej firmy pobierz narzędziem firma") and explains pagination via the after parameter. It does not differentiate from szukaj_firmy, the other search-oriented sibling, so an agent must infer whether to start from katalog or from that tool.

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