Return the list of NIPs you monitor, with their current VAT status and last-checked date. Each entry keeps the raw Ministry of Finance literal in status_vat and, when a status is known, adds derived language-neutral fields vat_active (boolean) and status_vat_code (active/exempt/not_registered). Requires a skanfirmy API key.
| Name | Required | Description | Default |
|---|---|---|---|
| api_key | No | skanfirmy API key (optional, if not in the header). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral disclosure burden and mostly succeeds: it reveals that status_vat preserves the raw Ministry of Finance literal and that derived fields are added only when a status is known. It does not mention pagination, empty-list behavior, or whether the call is read-only, but the opening 'Return' and no-mutation context make the intent fairly clear.
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?
Two sentences with no fluff. The core purpose is front-loaded, and the field-behavior detail is presented compactly. Every clause adds useful information.
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 simple list tool with one optional parameter and no output schema, the description covers the main return content and auth requirement well. It could add explicit read-only confirmation, pagination limits, or behavior when the list is empty, but these are minor gaps for this level of complexity.
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% for the single api_key parameter, so the schema already documents that it is optional and can be supplied in the header. The description only repeats that it requires a skanfirmy API key; it adds no new parameter-level semantics. Baseline 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 uses a specific verb (Return) and resource (the list of NIPs you monitor) and gives concrete output details: current VAT status, last-checked date, status_vat, vat_active, status_vat_code. It is easy to distinguish from siblings like observe_nip, unobserve_nip, and changes_since because it is the read-all-monitored view.
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 phrase 'NIPs you monitor' clearly states when this tool is appropriate: when the agent needs the current monitored set and its VAT statuses. It also notes the API-key precondition. It does not explicitly name alternatives or say when not to use it, so it misses the top criterion for a 5.
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.