Skip to main content
Glama

Backtesting Arena

by io.github.Schoasch
OverviewDiscussionsAdmin

Get Fear & Greed Index

arena_get_fear_greed

How fearful or greedy is the market right now? Crypto Fear & Greed Index (alternative.me). Returns the current value (0-100) and classification (extreme fear / fear / neutral / greed / extreme greed) as their own fields, plus history — the last 90 daily readings by default, so you can see whether today is a move or a plateau. The window is capped in SIZE but free in POSITION: end_date moves it anywhere in the history since 2018 (e.g. end_date=2025-10-06 reads the sentiment around the October 2025 top), and the range block states requested / granted / available days with the reason — a short series here is a window, not a young index. On Pro and Elite two Arena-derived blocks add what the upstream index does not publish: cadence (how far smoothed sentiment has travelled versus ~90 days ago) and tempo (how FAST the index is moving — 7d and 30d change ranked as a rolling percentile against three years of same-direction moves, not a fixed threshold; rank compares with its own history, not with "normal"). On Free both blocks are present but their values are null with a stated reason. For the regime around a reading use arena_get_cycle; for what followed comparable sentiment states use arena_get_historical_analog(preset="deep_fear"). [Free tier · cadence/tempo Pro+]

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
daysNoHow many daily readings to return (1-365, default 90). The full history since 2018 is deliberately not offered in one response — it is ~3,100 points and does not fit a tool response. The cap limits window SIZE, not position: combine with end_date to read any window since 2018.
end_dateNoLast day of the window (YYYY-MM-DD, inclusive). Positions the window anywhere in the history since 2018-02 — e.g. end_date=2025-10-06 answers "what was sentiment at the October 2025 top". Omit for a window ending today. value/classification/as_of describe the LAST day of the window; cadence/tempo (Pro+) compute on the history up to end_date only, never on later data.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / days / description
      Previous value: -"How many recent daily readings to return (1-365, default 90). The full history since 2018 is deliberately not offered here — it is ~3,100 points and does not fit a tool response."New value: +"How many daily readings to return (1-365, default 90). The full history since 2018 is deliberately not offered in one response — it is ~3,100 points and does not fit a tool response. The cap limits window SIZE, not position: combine with end_date to read any window since 2018."
    • addedInput schema / properties / end_date
      Added value: +{
+  "description": "Last day of the window (YYYY-MM-DD, inclusive). Positions the window anywhere in the history since 2018-02 — e.g. end_date=2025-10-06 answers \"what was sentiment at the October 2025 top\". Omit for a window ending today. value/classification/as_of describe the LAST day of the window; cadence/tempo (Pro+) compute on the history up to end_date only, never on later data.",
+  "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
+  "type": "string"
+}
  2. Changed3 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • 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. Changed2 schema fields changed
    • addedInput schema / $schema
      Added value: +"http://json-schema.org/draft-07/schema#"
    • addedInput schema / properties / days
      Added value: +{
+  "description": "How many recent daily readings to return (1-365, default 90). The full history since 2018 is deliberately not offered here — it is ~3,100 points and does not fit a tool response.",
+  "maximum": 365,
+  "minimum": 1,
+  "type": "integer"
+}
  4. First observed

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and meets it: it discloses the default 90-day window, the size/position semantics of days vs end_date, the range block's requested/granted/available behavior, tier-based nulls for cadence/tempo on Free, and how cadence/tempo are computed. It also warns against misreading a short series as a young index.

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?

The description is long but front-loaded with the core answer and then walks through output, window semantics, tier behavior, and siblings in a logical order. A few rhetorical flourishes (e.g., 'a move or a plateau') are not strictly necessary, but the density is high and every substantive claim supports correct use.

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?

There is no output schema, yet the description explains the shape of the response (value, classification, history, range, cadence, tempo) and the tier differences on top of the schema's parameter detail. It also covers edge semantics such as end_date positioning and Free-tier nulls, making it complete enough to invoke correctly without further documentation.

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 description coverage is 100% and the schema already documents days and end_date exceptionally well, including the 2018-02 position, the last-day semantics, and the cap-not-position rule. The description restates the same mental model but adds little literally new about parameter syntax or meaning, so the high-coverage baseline of 3 is appropriate.

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?

Description names the specific resource (Crypto Fear & Greed Index from alternative.me), the exact output fields (value, classification, history, cadence, tempo), and how it differs from adjacent tools by naming arena_get_cycle and arena_get_historical_analog. The 'get' verb is backed by concrete return content, so an agent knows immediately what this tool does.

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?

The description not only states when to use this tool ('to see whether today is a move or a plateau') but explicitly routes to alternatives: 'For the regime around a reading use arena_get_cycle; for what followed comparable sentiment states use arena_get_historical_analog(preset="deep_fear")'. This is explicit when/when-not guidance.

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