Skip to main content
Glama

Norman formation planner

Polish sole proprietorship (JDG) start plan

norman_pl_jdg_formation
Read-onlyIdempotent

Compares the three income tax forms for a new Polish sole proprietorship (JDG) for 2026: progressive scale, flat tax and lump-sum tax (ryczałt), each with social ZUS, health contribution, PIT and net income, from monthly revenue and costs and the founder's ZUS situation. Also returns the CEIDG, tax form, ZUS and VAT steps and continueInNorman, a link that opens Norman's JDG planner with these answers. situation: new = no business in the last 60 months and no work for a former employer (ulga na start, then preferential ZUS); recent = a business in the last 60 months (full ZUS); employment = also employed at least at the minimum wage (health contribution only); former_employer = the same work for this or last year's employer (full ZUS, ryczałt not available). Without lumpSumRate the ryczałt row is left out. Figures only: nothing is saved, and the result is general information without a recommendation of a tax form or ZUS scheme, not legal or tax advice. The inputs hold no personal data.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "country": "<country>",
      "year": "<year>",
      "monthlyRevenue": "<monthlyRevenue>",
      "monthlyCosts": "<monthlyCosts>",
      "situation": "<situation>"
    },
    "name": "norman_pl_jdg_formation"
  }
}

Input Schema

NameRequiredDescriptionDefault
cityNoCity of the business in Poland.
ideaNoThe user's business idea in their own words.
yearYesYear of the rules and rates: 2026.
countryYes
situationYesThe founder's ZUS situation: new, recent, employment or former_employer.
companyNameNoBusiness name (firma) the founder plans, if any.
lumpSumRateNoRyczałt rate in percent that applies to the activity; without it the ryczałt row is left out.
monthlyCostsYesExpected monthly business costs in złoty, net of VAT.
monthlyRevenueYesExpected monthly revenue in złoty, net of VAT.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnly=true, idempotent=true, destructive=false and openWorld=false, and the description adds genuinely new behavioural facts on top: nothing is persisted ('figures only: nothing is saved'), the output is general information with no recommendation of tax form or ZUS scheme, it is not legal or tax advice, and the inputs carry no personal data. Those are exactly the disclaimers and side-effect guarantees an agent needs before relaying results to a user.

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?

The most important content — what is compared and what is returned — is front-loaded, followed by the situation glossary and then the disclaimers. The situation definitions are long but each carries decision-relevant detail. Minor waste comes from repeating the lumpSumRate omission rule that already sits in the schema.

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

Completeness5/5

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

For a nine-parameter tool with no output schema, the description describes the shape of the result (per-form rows with ZUS, health contribution, PIT and net income, plus the step list and the continueInNorman link) and closes the loop on persistence, advice liability and personal data. An agent has everything needed to call it and to frame the answer correctly.

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

Parameters4/5

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

With schema coverage at 89% the baseline is 3, but the description earns more by expanding the 'situation' enum far beyond the schema's one-line gloss, tying each value to concrete ZUS/ulga na start consequences and to ryczałt eligibility. It also restates the lumpSumRate omission behaviour, which the schema already covers, so the gain is real though partly duplicative.

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?

The description opens with a specific verb and resource: it 'compares the three income tax forms' for a new Polish JDG in 2026 and enumerates them (progressive, flat, ryczałt) along with the cost components each row contains. It also names the artefact set returned (CEIDG, tax form, ZUS, VAT steps, continueInNorman), which distinguishes it from the sibling sp. z o.o. and German formation tools without ambiguity.

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?

The description gives concrete selection rules for the required 'situation' input, spelling out the factual conditions behind each value (no business in 60 months, business in last 60 months, employed at minimum wage, same work for former employer) and even flags that ryczałt is unavailable for former_employer. It also states the condition under which the ryczałt row disappears. What it does not do is explicitly route the agent away from the sibling formation tools, so it stops short of a full when/when-not statement.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources