Skip to main content
Glama

Backtesting Arena

by io.github.Schoasch
OverviewDiscussionsAdmin

Get Universe Detail

arena_get_universe

Which pairs are in this universe? Returns one pair universe in full: its id, label, selection rule and the complete list of pairs it currently contains. Use it to see what you are about to test BEFORE handing a universe_id to arena_run_universe_backtest, or to resolve a universe into explicit pairs. For the list of available universes call arena_list_universes. Without as_of the universe reflects the CURRENT membership (CoinGecko market-cap rank) — a backtest over it carries survivorship bias for the earlier years; the pit block in the payload says so. With as_of (YYYY-MM-DD, >= 2026-07-14) it returns the membership as MEASURED on that day from our own daily record of Binance USDT spot, ranked by 24h quote volume (not market cap) — coins delisted since are included, coins listed later are not. Point-in-time universes are recorded forward-only; earlier dates are refused, not reconstructed. [Free tier]

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
as_ofNoOptional YYYY-MM-DD. Point-in-time membership on that day (recorded since 2026-07-14, volume-ranked).
universe_idYesUniverse id, e.g. 'crypto-top-50'.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / as_of
      Added value: +{
+  "description": "Optional YYYY-MM-DD. Point-in-time membership on that day (recorded since 2026-07-14, volume-ranked).",
+  "type": "string"
+}
    • changedInput schema / properties / universe_id / description
      Previous value: -"Universe id, e.g. 'top-10-crypto'."New value: +"Universe id, e.g. 'crypto-top-50'."
  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"
-}
    • changedInput schema / required
      Previous value: -[
-  "universe_id",
-  "context"
-]New value: +[
+  "universe_id"
+]
  3. First observed

TDQS

A5/5.0
Behavior5/5

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

With no annotations provided, the description fully carries the burden of behavioral disclosure. It explains the survivorship bias without as_of, the forward-only nature of point-in-time universes, the rejection of earlier dates, and the difference in ranking methodology (market cap vs 24h quote volume). This is exemplary transparency for a tool with subtle behavioral nuances.

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

Conciseness5/5

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

While long, every sentence earns its place. The first sentence states the core purpose; subsequent sentences cover usage guidance, the as_of semantics, the bias warning, and the free tier. Information is front-loaded, and the structure flows logically from purpose to parameters to caveats. No fluff.

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?

The tool has inherent complexity (current vs point-in-time membership, survivorship bias, forward-only recording), and the description addresses all of it. It tells the agent exactly what is returned and how to interpret the as_of parameter. No output schema exists, so the description's explicit statement of the return fields ('id, label, selection rule and the complete list of pairs') covers that gap. Nothing an agent needs is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Even though schema description coverage is 100%, the description adds substantial meaning beyond the schema. For as_of, it clarifies the format, the minimum date (2026-07-14), the definition of 'measured on that day', and the consequence of using it (no survivorship bias). For universe_id, it implies the format via the example. This goes well beyond the schema's terse descriptions.

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 states a specific verb ('Returns') and resource ('one pair universe in full') and enumerates the exact fields (id, label, selection rule, complete list of pairs). It clearly distinguishes itself from arena_list_universes and arena_run_universe_backtest by naming them as siblings with different purposes.

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?

It explicitly tells when to use the tool: 'to see what you are about to test BEFORE handing a universe_id to arena_run_universe_backtest, or to resolve a universe into explicit pairs.' It also names the alternative for listing universes ('call arena_list_universes'). No ambiguity remains.

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