Skip to main content
Glama

finwire.pl - Polish financial data

Car insurance in Poland: average OC and AC premium (KNF)

get_car_insurance_market
Read-onlyIdempotent

Use for the average price of car insurance (OC and autocasco) in Poland, its trend and the size of the market. Tell the user that this is a market average and not a quote for one driver. Average car insurance premium in Poland from the quarterly KNF bulletin "Rynek ubezpieczeń" (part D): average gross written premium per policy for OC (motor third-party liability, insurance class 10) and autocasco (AC, class 3) over the last 4 quarters and in the last quarter, change vs a year earlier, policies written and in force, claims paid per 100 PLN of premium in the same window, claims paid per settled claim, the 18 non-life insurance classes, quarterly history and the finwire index finwire_oc_avg_premium. Amounts in PLN. These are market averages: they are not a price quote for a specific driver or car. Informational data, not insurance advice.

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": "get_car_insurance_market"
  }
}

Input Schema

NameRequiredDescriptionDefault
historyNoNumber of past quarters in the summary, default 8.

Output Schema

NameRequiredDescriptionDefault
urlYes
asOfNo
dataNo
titleYes
sourceYes
docsUrlYes
licenseYes
summaryYes
citationYes
datasetIdYes
sourceUrlNo
truncatedNo
serverDateYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4/5.0
Behavior4/5

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

Annotations already establish readOnly/idempotent/non-destructive/closed-world, so the bar is lower; the description still adds real context: the data is a quarterly market average per policy, amounts are in PLN, and it must be presented as a market average rather than an individual quote. It stops short of stating update cadence or how the quarterly history is bounded, but the safety profile is fully covered by annotations.

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

Conciseness3/5

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

Purpose and the key caveat are front-loaded, but the middle is one long run-on enumeration (claims per 100 PLN, claims per settled claim, all 18 non-life classes, finwire index) that is dense and partly redundant. The caveat is repeated almost verbatim ("not a quote for one driver" / "not a price quote for a specific driver"), which wastes space.

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 an output schema present and rich annotations, the description need not explain return shape; it supplies source, units, coverage and the critical interpretation caveat, so an agent can call and present it correctly. The only soft spot is that the field enumeration duplicates what the output schema already conveys.

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% and the single `history` parameter is documented in-schema with a default of 8 and a 0-60 range. The description only alludes to "quarterly history" without adding semantics for that parameter, so the baseline 3 applies.

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 first sentence names the specific resource (average OC and AC car insurance premium in Poland), plus the trend and market-size angle, and the body adds the exact source (KNF quarterly bulletin "Rynek ubezpieczeń", part D) and insurance classes (10 and 3). No sibling covers car insurance, so the domain alone separates it from get_credit_market or get_bank_rates.

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?

Explicitly frames when to use it ("Use for the average price of car insurance... its trend and the size of the market") and sets boundaries ("not a quote for one driver", "informational data, not insurance advice"), which also tells the agent how to relay results. No named alternative for per-driver quotes, but the exclusions cover the practical misuse case.

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.