Skip to main content
Glama

Trading Signals Toolkit

Macro Event Study (what happened last time)

event_study
Read-only

How ES/NQ/RTY/ZN moved +5/+15/+30/+60 min after each of the last N CPI, NFP (jobs), FOMC, PPI, retail sales, GDP or PCE releases (% and approx. points, ETF proxies from IEX historical data), with median/mean/80th/90th-percentile absolute moves, max adverse move, % of releases with a >0.5% 30-min move, up/down counts and the 80th-percentile absolute 15-minute move as a typical range size. Read-only, never places orders. Informational only, not investment advice.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "event": "<event>"
    },
    "name": "event_study"
  }
}

Input Schema

NameRequiredDescriptionDefault
eventYesRelease type: CPI, NFP (jobs report), FOMC (rate decision), PPI, RETAIL (retail sales), GDP, PCE
priceNoOptional current price so typical move sizes can be shown as price levels
symbolNoFutures root or ETF (default ES)
lookbackNoNumber of past releases (1-24, default 12)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / price / description
      Previous value: -"Optional current price, to express moves and the stop in points"New value: +"Optional current price so typical move sizes can be shown as price levels"
  2. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint, destructiveHint=false), and the description goes beyond them by disclosing data provenance and a real caveat: figures are derived from ETF proxies on IEX historical data, not the futures themselves, which materially affects interpretation. It restates read-only/no-orders, which is redundant with annotations, but the proxy and data-source disclosure is genuine added context. It does not state how far back data availability extends or how releases are timestamped.

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?

The entire substance is packed into one very long run-on sentence dense with slash-separated statistics, followed by two short qualifier sentences. Content is largely substantive, but the structure is not front-loaded — the core 'what it does' is buried inside a metrics list that would read better as a separate summary line.

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 carries the burden of describing return values, and it does so thoroughly: medians, means, 80th/90th-percentile absolute moves, max adverse move, up/down counts, and a typical range size. Remaining gaps are minor — no statement of session/timezone alignment, sample-size caveats for small lookbacks, or coverage start date.

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%, so every parameter (event enum, symbol enum, lookback 1-24, price) is already documented in the schema, making 3 the baseline. The description adds only marginal meaning — it clarifies that symbol values are futures roots or ETF proxies and that lookback counts 'last N releases' — but adds nothing about how price is used beyond what the schema field says.

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 a specific analytical operation (historical reaction of ES/NQ/RTY/ZN at +5/+15/+30/+60 min horizons) applied to a specific resource set (CPI, NFP, FOMC, PPI, RETAIL, GDP, PCE releases). It is unmistakable against siblings like event_gate or pre_trade_check, which by name imply prospective gating rather than retrospective base rates.

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 title '(what happened last time)' and the statistics listed suggest this is for establishing base-rate expectations ahead of an event, but the description never says 'use this when X' or names an alternative such as event_gate. No exclusions, prerequisites, or timing guidance are given.

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