Skip to main content
Glama

Real-Time Inflation: the live US CPI nowcast, its parts, the odds and what CPI day did to Bitcoin and gold

get_inflation
Read-only

OwlChart Real-Time Inflation in one tool (v5.897): what=now (the OwlChart nowcast of the coming US CPI print, month on month and year on year, headline and core, one word COOLING, STEADY or HEATING against the last official print, the Cleveland Fed nowcast for CPI, core CPI, PCE and core PCE with its date, the last official CPI, core CPI, PCE, core PCE and PPI, and the countdown to the next CPI, PPI, PCE and Fed decision), components (live oil, petrol, heating oil, corn, wheat, soybeans, cattle and hogs futures, the weekly US pump price and its drag on the headline CPI, and the official monthly parts: energy, food, shelter, rent, used cars, goods, services, producer prices, hourly earnings, the 5 and 10 year breakeven rates and the Michigan survey, each with a freshness label LIVE, DAILY, WEEKLY or MONTHLY and a cooling or heating arrow), history (the OwlChart nowcast kept once a day and never rewritten, against the official print for every month since launch, with the miss), calendar (CPI, PPI, PCE, jobs report and Fed decisions with countdowns), market (Kalshi odds for the next CPI by range with the middle of the market, and Fed hike, hold and cut odds), reaction (what Bitcoin, gold, the dollar index and the 2 year yield did on every CPI release day of the last three years, grouped by whether the print came in cooler or hotter than the Cleveland Fed nowcast) or brief (the plain read and the crypto and gold box). The consensus is not shown: no raw source publishes it. Data, not advice. Page: https://owlchart.com/inflation.html

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_inflation"
  }
}

Input Schema

NameRequiredDescriptionDefault
whatNowhich inflation data set, default brief

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.6/5.0
Behavior4/5

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

Beyond the readOnly/openWorld annotations, the description discloses meaningful behavior: the nowcast history is 'kept once a day and never rewritten' (immutability), every component carries a freshness label (LIVE/DAILY/WEEKLY/MONTHLY), and the consensus is explicitly absent because no raw source publishes it. 'Data, not advice' also sets expectations. It does not say how the result is delivered (text block vs chart reference), which keeps it short of a 5.

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

Conciseness2/5

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

The body is a single enormous run-on sentence with deeply nested parentheticals, which makes it hard to scan and easy for an agent to mis-parse. It is informative, but the same content would be far more usable as a short front-loaded summary followed by per-mode bullets.

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?

For a single-optional-parameter tool with no output schema, the description covers all seven modes thoroughly, states data provenance and limitations (no consensus, freshness labels), and explains the nowcast's methodology constraints. What's missing is minor: the default mode, and any indication of the output's form or size.

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, but the description adds real meaning the schema's one-line enum doc does not: each enum value is expanded into a list of what that mode returns (components, history with miss, Kalshi odds, reaction grouped by cooler/hotter than the Cleveland Fed nowcast). The only gap is that the default ('brief') stated in the schema is not repeated or explained beyond 'the plain read and the crypto and gold box'.

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

Purpose4/5

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

The description names a specific resource (the OwlChart real-time US CPI nowcast) and enumerates the exact contents of each of the seven modes, so an agent can tell this is an inflation nowcast tool rather than a price-history or news tool. It loses a point only because the framing is marketing-style ("Real-Time Inflation in one tool (v5.897)") rather than a crisp verb-plus-resource statement.

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?

The per-mode descriptions imply when each dataset is appropriate (e.g. 'reaction' when you want CPI-day moves in Bitcoin and gold, 'calendar' for countdowns), which is useful implied guidance. But there is no explicit when-to-use/when-not guidance versus siblings, and the description never states that 'brief' is the default when 'what' is omitted — the schema does, not the description.

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