Skip to main content
Glama
Sign In

skanfirmy.pl

by io.github.bartosz-kuc
OverviewDiscussionsAdmin

changes_since

Read-onlyIdempotent

Return changes (VAT status, bank accounts, or registry data — name, address, KRS, REGON — from the White List) detected since a given date for the NIPs you monitor. The field property is one of: status_vat, account_added, account_removed, name, address, krs, regon. For natural persons (entities without a KRS number; natural_person: true) only status_vat, account_added and account_removed are returned, account numbers are masked (check digits + last 4, e.g. 61…2874) and name is null (GDPR); check a specific account with sprawdz_rachunek. A polling channel for agents. Requires a skanfirmy API key.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "changes_since"
  }
}

Input Schema

NameRequiredDescriptionDefault
sinceNoISO date/timestamp (e.g. 2026-08-01). Returns changes since that date. Defaults to the beginning.
api_keyNoskanfirmy API key (optional, if not in the header).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Adds substantial behavior beyond the readOnly/idempotent annotations: GDPR masking of account numbers with the exact format (check digits + last 4), name forced to null for natural persons, a restricted field set for entities without KRS, and the API-key requirement. It does not discuss rate limits or whether results are paginated, but the domain-specific caveats are unusually well disclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the core purpose and packs the exception rules efficiently into a single paragraph with no filler sentences. It is dense but readable; the only wasted content is the field-value enumeration for a parameter absent from the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description does the necessary work of explaining what comes back (change field values, masked account numbers, null names) and the auth requirement. Remaining gaps are minor: the response envelope (list vs object, ordering, maximum window) is not described.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so since and api_key are already documented, giving a baseline of 3. The description does add that since defaults to the beginning, but it also spends a sentence enumerating 'the field property' values that do not exist in the supplied input schema, which adds confusion rather than meaning for the two real parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Return changes ... detected since a given date for the NIPs you monitor') and enumerates exactly which change categories are covered (VAT status, bank accounts, registry data). It also differentiates itself from sprawdz_rachunek for single-account checks, so an agent can place it without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Framed clearly as 'a polling channel for agents' scoped to NIPs you monitor, with the alternative sprawdz_rachunek named for checking a specific account. It stops short of explicit when-not-to-use guidance (e.g. relationship to list_observations or observe_nip for setting up the watchlist), leaving that to inference.

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

All skanfirmy.pl toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources