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

No annotations exist, so the description carries the full behavioral burden and does well on the unusual parts: it discloses the upstream data source and the price ($0.25 USDC). It leaves gaps on failure behavior (what is returned for an unknown or deregistered KRS) and on any rate limits or latency, which matter for a paid call.

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?

Tight and front-loaded: identity and source first, inputs next, payload fields next, exclusion and examples last. The telegraphic sentence fragments are efficient but make 'pl' and 'number' invisible, so the compression costs a little clarity.

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, listing the retrieved fields (name, legal form, seat, PKD, representation, capital, red flags) is valuable and well placed. But for a paid, unannotated tool the definition still leaves undefined what 'pl' and 'number' are for, whether one identifier is mandatory, and what a not-found response looks like.

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 0% across 4 parameters, so the description must compensate — and it does for two of them, adding format constraints ('krs (10 digits)') and examples. However 'pl' and 'number' are never mentioned, and with zero required parameters the description also fails to state that at least one of krs/nip must be supplied; half the surface stays ambiguous.

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 ('Polish company lookup'), names the authoritative source (KRS current extract, api-krs.ms.gov.pl), and enumerates the returned data. Combined with the country-prefixed sibling set (au_company, uk_company, fr_company...), an agent can immediately tell this is the Poland-specific option.

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 concrete invocation paths (by 10-digit KRS, or by NIP resolved through the MF whitelist to a KRS) with worked examples for both, and explicitly excludes an approach ('No free-text name search'). It stops short of routing to any alternative tool for name-based discovery, so the when-not guidance is partial rather than complete.

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