Skip to main content
Glama

Backtesting Arena

by io.github.Schoasch
OverviewDiscussionsAdmin

Get Macro Regime Snapshot

arena_get_macro_regime

What is the macro backdrop doing? Daily Macro Regime snapshot from 18 components in 6 tiers (Liquidity 30%, Financial Conditions 20%, Risk Appetite 15%, Crypto Liquidity 10%, Business Cycle 15%, Inflation/Real Rates 10%). FRED-sourced. Returns composite_score (0-100), regime_label (risk_off/neutral/risk_on_leaning/risk_on), cycle_phase_label (contraction/early_expansion/mid_expansion/late_expansion), matrix_quadrant (sweet_spot/late_cycle_warning/crisis/recovery), tier_scores (6 sub-scores), components (flat key/value of all 18), plus stale_components_detail dating each stale input (last_good_date + age_days + discontinued flag for series the upstream has retired for good) so freshness is quantified, not a vague caveat. Two component keys mean something narrower than their name suggests, so read them carefully: vix_score is the derived 0-100 score (a value of 71 means VIX around 18.6), NOT the VIX index level — the raw Cboe level is not redistributed over this channel; and broad_dollar_index is FRED DTWEXBGS (Broad USD Index, Jan 2006 = 100), NOT the ICE DXY, so readings near 120 are normal. fed_funds_rate is FRED FEDFUNDS, the monthly AVERAGE effective rate (lags; not the daily DFF, not the target range); global_m2_yoy is NOT M2 but the YoY change of G3 central-bank balance sheets (Fed+ECB+BoJ in USD) — it can fall while US M2 hits a record. component_notes carries these definitions in the payload. The former names vix and dxy were removed on 2026-09-01 after their announced deprecation window; consumer_confidence_value went with them (OECD retired the series, frozen since 2024-01-01, never weighted in the composite). provenance says how many of the 18 weighted components formed today’s composite (grade full/partial/thin; null for rows written before 2026-10-13, when coverage was not recorded); missing components drop out and the tier renormalizes, a tier with no input at all scores a stand-in 50 and is named in degraded.empty_tiers. Pass fields="full" for the named missing components, sources and per-tier provenance. move_index and fed_funds_cuts_priced are always null and never weighted — slots without a source, not outages. [Free tier]

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fieldsNoOmit for the default response, which carries `provenance` in short form (grade full/partial/thin, sources_used, sources_expected). 'full' adds the long form: sources_missing (named), sources (licence attribution names), grade_reason, as_of — plus per-part provenance where the composite has parts. A `thin` grade (under half the expected inputs) is never a basis for a verdict or a ranking.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / $schema
      Added value: +"http://json-schema.org/draft-07/schema#"
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / fields
      Added value: +{
+  "description": "Omit for the default response, which carries `provenance` in short form (grade full/partial/thin, sources_used, sources_expected). 'full' adds the long form: sources_missing (named), sources (licence attribution names), grade_reason, as_of — plus per-part provenance where the composite has parts. A `thin` grade (under half the expected inputs) is never a basis for a verdict or a ranking.",
+  "enum": [
+    "full"
+  ],
+  "type": "string"
+}
  2. Changed2 schema fields changed
    • removedInput schema / properties / context
      Removed value: -{
-  "description": "Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\"",
-  "type": "string"
-}
    • removedInput schema / required
      Removed value: -[
-  "context"
-]
  3. First observed

TDQS

A4/5.0
Behavior5/5

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

With no annotations and no output schema, the description carries the full behavioral burden and does so thoroughly: it discloses the weights/tiers, that missing components drop out and tiers renormalize, that an empty tier scores a stand-in 50 (degraded.empty_tiers), that move_index and fed_funds_cuts_priced are always null and never weighted, the provenance grading semantics including null for pre-2026-10-13 rows, and stale_components_detail fields. This is exactly the kind of non-obvious output behavior an agent could not infer from structured fields.

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?

It is front-loaded with the one-line purpose before the detail, and nearly every sentence carries load-bearing output semantics (the vix_score and broad_dollar_index pitfalls, deprecation dates, null slots). Still, it is a single dense block that would read faster as short bulleted sections.

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?

For a tool with no output schema, the description supplies everything needed to interpret the response: all named return fields, the counter-intuitive component definitions, staleness quantification, provenance/degradation semantics, and null-slot explanations. Nothing material an agent needs to call or read it correctly is missing.

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?

Only one parameter (fields, enum 'full') and schema description coverage is 100%, so the schema already documents omission vs 'full' and the thin-grade caveat. The prose ('Pass fields="full" for the named missing components, sources and per-tier provenance') restates the schema rather than extending it, so the baseline 3 applies.

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 states a specific verb+resource ('Daily Macro Regime snapshot from 18 components in 6 tiers') and enumerates the exact payload fields, so an agent knows precisely what this returns versus a generic market snapshot. It never names a sibling tool or an explicit exclusion (e.g. arena_get_cycle, arena_get_fear_greed), so differentiation rests on content specificity rather than routing language.

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 by the lead question ('What is the macro backdrop doing?') and the [Free tier] tag, and the fields='full' hint gives a conditional calling pattern. There is no 'when to use this vs alternative' guidance and no prerequisites or exclusions despite ~40 sibling tools covering overlapping macro/sentiment ground.

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

All Backtesting Arena toolsInspect
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.

Resources