finwire.pl - Polish financial data

finwire lead forecasts: core inflation and impaired loans

get_lead_forecasts

Read-onlyIdempotent

Two finwire.pl models with 80% intervals. finwire_cost_pressure (Presja kosztowa finwire): NBP core inflation y/y in 6 and 12 months from a unit labour cost proxy, producer prices and the EUR/PLN change. finwire_npl_forecast (Stres kredytowy wyprzedzający finwire): share of impaired (IFRS 9 Stage 3, KNF) housing and consumer loans in 2 and 4 quarters from the WIBOR 3M change, unemployment and the portfolio trend. A forecast is shown only when at least 70% of actual readings fell inside the 80% interval in the rolling backtest; otherwise published is false and only the accuracy statistics are given. A model estimate, not investment 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_lead_forecasts"
  }
}

Input Schema

Name	Required	Description	Default
`index`	No	One index; omit for both.

Output Schema

Name	Required	Description	Default
`url`	Yes
`asOf`	No
`data`	No
`title`	Yes
`source`	Yes
`docsUrl`	Yes
`license`	Yes
`summary`	Yes
`citation`	Yes
`datasetId`	Yes
`sourceUrl`	No
`truncated`	No
`serverDate`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 4, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare the read-only, idempotent, non-destructive profile, so the description earns credit for the conditional-output rule: forecasts are published only when >=70% of actuals fell inside the 80% interval in the rolling backtest, otherwise published is false with statistics only. This is exactly the kind of surprising behavior an agent needs warned about before interpreting results.

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 publication-gate caveat is front-loaded in the middle of a single dense paragraph and every clause carries information. The Polish parenthetical names (Presja kosztowa finwire, Stres kredytowy wyprzedzający finwire) add length without much selection value for an agent.

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?

With an output schema present, return values need no explanation, and the description covers methodology, forecast horizons, the publication condition, and the not-investment-advice caveat. Nothing an agent needs to select or interpret this tool is missing.

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?

Schema coverage is 100% and the single enum parameter is fully documented there, so a 3 baseline would suffice. The description goes beyond by explaining what each model actually forecasts and from which drivers, which lets the agent pick 'cost-pressure' vs 'npl' meaningfully rather than guessing from enum labels.

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 names the two concrete models (finwire_cost_pressure, finwire_npl_forecast) and states exactly what each projects (NBP core inflation y/y at 6/12 months; IFRS 9 Stage 3 impaired loan share at 2/4 quarters) plus their inputs. An agent can distinguish this from siblings like get_nowcast or get_macro_indicator without opening a schema.

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

Usage Guidelines3/5

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

Usage is only implied: the 70% backtest rule tells the agent a forecast may be absent and only accuracy statistics returned, and the closing line flags it as a model estimate rather than advice. There is no explicit statement of when to reach for this tool instead of the sibling nowcast/indicator tools.

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

All finwire.pl - Polish financial data tools Inspect

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.