Skip to main content
Glama

Backtesting Arena

by io.github.Schoasch

Robustness Field — plateau vs. spike + Deflated Sharpe with a counted N

arena_get_robustness_field

Is this backtest result real, or a lucky cell? Assess one backtest result against its neighborhood instead of trusting a single "+X% CAGR" cell. Given a (strategy, interval, pair) and YOUR result (user_cagr, optional user_sharpe), returns: the cross-asset distribution of the SAME strategy+interval across every pair the backtest factory ran it on (median, IQR, positive-share, your percentile), a plateau/spike/fragile/mixed verdict, and — where Sharpe coverage allows — a Deflated Sharpe threshold whose N is COUNTED (the number of neighbor assets IS the testing family), not guessed. Honest small-n handling: fewer than 15 neighbors → "insufficient", no DSR-N claimed. Set axis="parameter" for the secondary, always-anecdotal view (the few parameter settings tested on this exact pair). Read-only over result aggregates, look-ahead free. [API Pro tier]

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
axisNoNeighborhood axis. 'cross_asset' (default, dense, carries the verdict + DSR-N) or 'parameter' (secondary, always anecdotal — the parameter settings tested on this one pair).cross_asset
pairYesTrading pair of your cell, e.g. 'BTCUSDT'.
paramsNoOptional: numeric strategy parameters of your cell. Only numeric params define the neighborhood; matched per pair where the factory ran them.
intervalYesCandle interval, e.g. '1d', '1w', '1M'.
strategyYesStrategy key, e.g. 'rsi_sma'.
user_cagrYesYour result: CAGR in percent (e.g. 41 for +41%) — the cell being assessed.
asset_typeNoAsset class filter (default 'crypto').
user_sharpeNoOptional: your annualized Sharpe (result_sharpe scale). Used for the counted-N Deflated Sharpe where neighbor coverage allows.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 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: -[
-  "strategy",
-  "interval",
-  "pair",
-  "user_cagr",
-  "context"
-]New value: +[
+  "strategy",
+  "interval",
+  "pair",
+  "user_cagr"
+]
  2. Added

TDQS

A4.9/5.0
Behavior5/5

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

With no annotations, the description fully owns behavioral disclosure. It reveals that the tool is read-only and look-ahead free, states the honest small-n handling (no DSR-N claimed under 15 neighbors), and explicitly labels the parameter axis as 'always anecdotal'. It also explains the counted-N logic for DSR, providing a complete picture with no contradictions.

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?

The description is dense but every sentence carries value: the hook, the input, the output, the caveat about small-n, and the axis distinction. It is front-loaded with the core question and adds specifics in a natural progression, with zero filler or redundancy.

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?

Given the tool's complexity (8 params, nested object, no output schema), the description is remarkably complete: it explains the output shape (distribution metrics, verdict, DSR threshold), the edge case handling, and the semantic difference between axes. An agent can confidently call this tool without additional inference.

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 coverage is 100%, so each parameter is already documented. The description adds meaning by explaining the conceptual role of params ('Only numeric params define the neighborhood'), how user_sharpe feeds into the counted-N DSR, and what axis values mean. This goes beyond a bare schema listing, though it doesn't re-explain each field individually.

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 opens with a direct, specific question ('Is this backtest result real, or a lucky cell?') and a clear verb ('Assess one backtest result against its neighborhood'). It names the exact resource (a strategy+interval+pair cell) and what it returns (distribution, verdict, DSR), making it unmistakably distinct from sibling tools like arena_get_backtest or arena_is_distinguishable, even without naming them.

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 explicitly contrasts this tool with a naïve approach ('instead of trusting a single "+X% CAGR" cell'), giving a clear when-to-use. It also provides conditional guidance: 'Set axis="parameter" for the secondary, always-anecdotal view' and explains the small-n rule ('fewer than 15 neighbors → "insufficient"'). This is actionable and non-ambiguous.

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
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.6/5.0
Disambiguation2/5

Many tools cover overlapping market indicators (e.g., cycle state, pulse, bullmarket ampel, volatility phases) and several share similar get_*_history patterns, which could cause an agent to select the wrong one. However, each tool has detailed descriptions with explicit references to related tools to reduce ambiguity.

Naming Consistency3/5

Tool names generally follow a verb_noun pattern (arena_get_*, arena_list_*, arena_run_*, arena_subscribe_*), but there are inconsistencies such as 'validate_strategy' (no arena_ prefix), 'arena_status' (not a clear verb_noun), and variations like 'arena_run_grid_backtest' vs 'arena_run_backtest'.

Tool Count2/5

With 84 tools, the server is heavily over-scoped for a typical MCP server, likely causing navigation and selection overhead. While the domain (crypto backtesting and analytics) is broad, 84 tools exceed reasonable coherence and impose a high cognitive load.

Completeness4/5

The tool surface covers a wide range of analytics (market indicators, backtesting, validation, alerts, subscriptions, reports) with few obvious dead ends. Minor gaps exist like lack of direct portfolio management or strategy editing, but core workflows are well covered.

Resources