Skip to main content
Glama

QE Virtual AI Machine: one liquidity machine per country, its money pipes and the exact repair of each one

get_liquidity
Read-only

The OwlChart QE Virtual AI Machine (v5.910), one machine per country, each read only from that country's own institutions. what=countries (the World board: 43 economies in a fixed order, the United States, the euro area, the 27 members of the European Union, then the United Kingdom, Japan, China, Georgia, Ukraine, Russia, Iran, Australia, New Zealand, South Korea, North Korea, Cuba, Pakistan and Nicaragua; each with its gauge from 0 to 100 or no gauge, its word DRYING, TURNING or FLOODING, how many of its wired pipes are flowing, the date of its latest report, and the scoring formula). With country= a two letter code (us, de, fr, es, it, pl, gb, jp, cn, ge, ua, ru, ir and the other members of the European Union): what=now (the gauge, the word, the counts, two plain sentences, the latest and the next report, the formula), pipes (that country's own pipes, each tagged national or euro-area shared, with its source, official page, series, raw value, date and raw data link; a pipe whose national source is not wired is grey and names the office it waits for; globalOverlay holds stablecoins, Bitcoin funds and gold, which are never counted in any gauge), repairs (what would turn each leaking pipe green and the next date), log (reports that changed a pipe), brief, history (one reading a day). what=wars (the two wars of the Global overlay, Middle East and oil, Russia and Ukraine with gas and food: the world prices and the repair orders, who holds each lever and the proof; shown on every country and never counted in a number). what=method (the exact scoring formula, weights, freshness limits). A country shows a number only when every one of its own pipes has a fresh signal; otherwise it reads being wired. Data only, not 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_liquidity"
  }
}

Input Schema

NameRequiredDescriptionDefault
whatNowhich data set, default countries
countryNothe country, a two letter code: us, at, be, bg, hr, cy, cz, dk, ee, fi, fr, de, gr, hu, ie, it, lv, lt, lu, mt, nl, pl, pt, ro, sk, si, es, se, gb, jp, cn, ge, ua, ru, ir

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / country / description
      Previous value: -"the country: us United States, es Spain, ge Georgia"New value: +"the country, a two letter code: us, at, be, bg, hr, cy, cz, dk, ee, fi, fr, de, gr, hu, ie, it, lv, lt, lu, mt, nl, pl, pt, ro, sk, si, es, se, gb, jp, cn, ge, ua, ru, ir"
    • removedInput schema / properties / country / enum
      Removed value: -[
      -  "us",
      -  "es",
      -  "ge"
      -]
    • changedInput schema / properties / what / enum
      Previous value: -[
      -  "countries",
      -  "now",
      -  "pipes",
      -  "repairs",
      -  "log",
      -  "brief",
      -  "history",
      -  "country"
      -]New value: +[
      +  "countries",
      +  "wars",
      +  "method",
      +  "now",
      +  "pipes",
      +  "repairs",
      +  "log",
      +  "brief",
      +  "history"
      +]
  2. Added

TDQS

B3.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint, so the safety bar is low. The description nonetheless adds genuine behavioral rules beyond them: data is read only from each country's own institutions, a country shows a number only when every one of its own pipes has a fresh signal and otherwise reads 'being wired', grey pipes name the missing office, globalOverlay items are never counted in any gauge, and the output is 'data only, not advice'. Those are real disclosure of gating logic an agent could not infer from annotations.

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 text is a single sprawling block of run-on sentences with nested parentheticals listing 43 economies and every EU country code, plus an irrelevant version number. The valuable rules (freshness gating, overlay exclusion, not-advice disclaimer) are stranded at the end rather than front-loaded. Conciseness here is not under-specification but over-stuffing: much of the enumeration belongs in schema or nowhere.

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 no output schema, the description must cover return content, and it does for every what value, including the notional overlay, method, and the 'being wired' fallback state. Combined with a 2-parameter, 100%-covered schema, an agent has enough to call this correctly. It loses points only because the delivery format makes that completeness hard to extract rather than because anything material 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 description coverage is 100% and the enum already lists the nine what values and the country codes, so the baseline would be 3. The description earns above baseline by explaining what each selector actually yields (e.g. log = 'reports that changed a pipe', history = 'one reading a day', repairs = 'what would turn each leaking pipe green and the next date') and by noting countries defaults and that country accepts two-letter codes. That is meaning the schema's bare enum labels do not carry.

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

Purpose3/5

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

The description does convey that this returns liquidity-machine readings per country, but the actual purpose statement is buried inside a version-branded title prefix ('The OwlChart QE Virtual AI Machine (v5.910)') followed by a long enum dump. It never states a clean verb-plus-resource sentence and never distinguishes itself from plausible siblings such as get_liquidity_heatmap or get_money_flows. An agent can eventually infer the purpose but must parse a wall of parentheticals to get there.

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 implied through per-value explanations: what=countries for the World board, what=now for a single country's gauge and prose, pipes/repairs/log/brief/history for drill-downs, wars for the overlay, method for the formula. That effectively tells an agent which selector to choose. However, there is no explicit when-not-to-use, no named alternatives, and no statement of prerequisites or call order (e.g. that country= is only meaningful for certain what values).

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