Look up entity data in the REGON register (Statistics Poland / GUS BIR) by NIP: REGON number, official name, legal form (legal or natural person), full address (voivodeship, county, municipality). Covers ALL entities, including sole proprietors that are not in the KRS.
| Name | Required | Description | Default |
|---|---|---|---|
| nip | Yes | 10-digit Polish NIP (tax ID). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the burden. It does this well by using the non-mutating verb 'look up', naming the official source (GUS BIR), and disclosing the scope of coverage and returned data. It does not describe error behavior or availability, but for a simple read-only lookup the main behavioral traits are covered.
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 description is a single well-structured sentence with the action and target front-loaded. The output fields are listed compactly, and the important coverage caveat about sole proprietors not in KRS earns its place. There is no filler.
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 with no output schema, the description is largely complete: it explains the input, the source, the returned fields, and the scope of entities covered. It could optionally mention error cases or explicitly compare against sibling tools like sprawdz_nip, but these are not essential for correct invocation.
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%, and the schema already describes 'nip' as a 10-digit Polish NIP. The description only restates that the lookup is by NIP and adds no format, validation, or usage nuance beyond what the schema provides, so the baseline score of 3 is appropriate.
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 names a specific action ('Look up entity data'), a specific resource ('REGON register (Statistics Poland / GUS BIR)'), and lists the concrete result fields: REGON number, official name, legal form, and full address. The final clause about covering ALL entities, including sole proprietors not in KRS, helps distinguish this from similar NIP-lookup tools.
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?
The description gives clear context for when this tool is appropriate: lookup by NIP against the REGON register, with broad coverage that includes sole proprietors outside KRS. It does not explicitly name alternatives or state when not to use it, so it stops short of full alternative-routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have distinct purposes: checking a single NIP, bulk-checking NIPs, checking a bank account, validating VIES, and searching registers are clearly separated. Some minor overlap exists between sprawdz_nip and sprawdz_lista_nip, and between changes_since and list_observations, but the descriptions clarify the individual vs. bulk and change-history vs. current-state distinctions.
Naming mixes English verbs (observe_nip, list_observations, set_webhook) with Polish verbs (generuj_mikrorachunek, oblicz_odsetki, sprawdz_nip, szukaj_pkd), making the convention feel inconsistent. Additionally, changes_since is a noun phrase rather than a verb-based action, breaking the overall verb_noun pattern.
14 tools is well within a reasonable range for a business-information and monitoring server. Each tool corresponds to a distinct operation, and the number feels appropriate for the scope of checking Polish business registers, VAT validation, interest calculation, and NIP monitoring.
The tool surface covers the core domain well: single and bulk VAT checks, bank account verification, REGON and VIES lookups, PKD search, micro-account generation, interest calculation, and a full monitoring lifecycle (observe, list, changes, webhook, unobserve). Minor gaps exist, such as no dedicated webhook-status listing and limited detailed KRS fetching, but agents can accomplish expected workflows.