Skip to main content
Glama

finwire.pl - Polish financial data

Polish savings bond rate in the next interest period

get_bond_next_rate
Read-onlyIdempotent

Use for the rate of Polish savings bonds (EDO, COI, ROR, DOR, ROS, ROD) in the next interest period, for example "what will my EDO pay from December" or "what will COI pay in the next year". If the user gives the purchase month, use type and purchase_month. If the state is estimate, tell the user that it is a model estimate. If the state is unknown, give knownFrom. Finwire Bondcast (finwire_bond_next_rate): the interest rate of Polish State Treasury retail savings bonds in the next interest period, from the rules in the Ministry of Finance issue letters. COI, EDO, ROS and ROD from the 2nd year: margin + GUS CPI y/y for month M-2 (M = first month of the period), zero if CPI is negative. ROR and DOR each month: NBP reference rate on the 10th working day before the month + margin. Each period has a state: announced (Ministry of Finance interest table), known (rate from the formula with a published input), estimate (GUS flash CPI, Finwire Nowcast CPI with an 80% interval, or scenarios of the next RPP decision) or unknown (no number; knownFrom gives the date of the exact rate). Without arguments: the index (2nd year of EDO bought 12 months before next month), periods that start in the next 3 months by bond type, the formula inputs and how the Ministry of Finance followed RPP decisions. With series, or with type and purchase_month: all interest periods of that series. A series code is the type + month and year of maturity (EDO bought in December 2025 = EDO1235). Informational data, 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_bond_next_rate"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeNoBond type. Use with purchase_month when the user does not know the series code.
seriesNoSeries code, e.g. EDO1235, COI1129, ROR1127 (type + MMYY of maturity).
purchase_monthNoMonth of purchase 'YYYY-MM'. Use with type.

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

A4.7/5.0
Behavior5/5

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

Annotations already cover read-only, idempotent and closed-world, but the description adds far more: the four result states (announced/known/estimate/unknown), the formulas behind COI/EDO/ROS/ROD and ROR/DOR, the meaning of knownFrom, and the explicit 'informational data, not investment advice' caveat. This is exactly the kind of provenance and uncertainty information annotations cannot express.

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?

Usage guidance is correctly front-loaded, but the body is a dense block that mixes selection guidance, formula mechanics, state definitions and caveats. The formula and market-notation detail is helpful for interpretation but is close to overload for a three-parameter read tool.

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, the description does not need to describe return values, and it doesn't. It still covers default behavior, state semantics, series-code format and the informational caveat, leaving nothing an agent needs in order to call it correctly or interpret the response.

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%, so the baseline is 3; the description earns an extra point by explaining the series-code convention, including the non-obvious mapping that EDO bought in December 2025 is EDO1235 (type plus month/year of maturity). It also ties type and purchase_month together as a pair, which the schema only hints at.

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: the rate of named Polish savings bonds (EDO, COI, ROR, DOR, ROS, ROD) in the next interest period, with concrete example queries. Nothing about it could be confused with siblings such as get_savings_bond_sales or get_interest_rates.

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

Usage Guidelines5/5

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

Gives explicit routing rules: use type plus purchase_month when the user supplies the purchase month, use series (or the two together) to get all periods of one series, and spell out the no-argument default behavior. It also says what to tell the user for the estimate and unknown states, so the agent knows not just when to call it but how to present the result.

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.