Skip to main content
Glama

Backtesting Arena

by io.github.Schoasch

Get Edge Library — Filter Effect Reports

arena_get_edge_reports

Which entry filter carries a real edge? Platform-wide aggregated analysis: how each Pro+ entry filter (200 WMA, ATR low/high/expansion, Altcoin Season, Bullmarket confirm/strict) affects strategy CAGR — baseline vs. filtered, asset-equal-weighted (per-asset medians over param-deduplicated runs, then the median across assets — no single asset's run grid can dominate an arm). delta_cagr is the median of PER-ASSET deltas over MATCHED assets only (present in both arms) — so it usually differs from filtered_cagr − baseline_cagr; pairs_matched/pairs_filtered and the baseline pairs count declare the basis. Verdicts come from the effect's 90% paired-bootstrap interval (delta_ci_low/delta_ci_high), not the point estimate: helps (whole interval > +1pp) / hurts (< −1pp) / neutral (inside ±1pp) / insufficient_evidence (runs disagree) / insufficient_data (fewer than 30 runs per arm or fewer than 10 matched assets). Below the gate, derived fields (delta_*, dsr, dsr_pass) are null; every gated null carries its reason (dsr_pass_reason, *_net_reason); the envelope evidence block declares the gate's referent and threshold machine-readably. Response is GROUPED by strategy: envelope fields (market, computed_at, n_trials) once, per strategy one baseline block {cagr, net_cagr, sharpe} plus filter cells; filter cells with zero runs are folded into filters_without_data. A full market is a few hundred cells — use limit/offset (strategies per page) plus the truncated flag for partial reads. Filters evaluated in isolation (no stacking); net values are median CAGR after per-side trading costs (verdict/delta stay gross). [Free tier]

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoStrategies per page (1–100). Omit for all.
marketYesMarket to analyze (crypto or tokenized).
offsetNoStrategies to skip (paging).
verdictNoFilter by verdict. Default 'all'. Note 'insufficient_evidence' is NOT the same as 'insufficient_data': the former has enough runs but they disagree (the effect's 90% interval straddles the ±1pp line), the latter simply lacks runs.
strategyNoRestrict to a single strategy key (e.g. golden_cross). Omit for all strategies.

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: -[
-  "market",
-  "context"
-]New value: +[
+  "market"
+]
  2. Changed2 schema fields changed
    • addedInput schema / properties / limit
      Added value: +{
+  "description": "Strategies per page (1–100). Omit for all.",
+  "maximum": 100,
+  "minimum": 1,
+  "type": "integer"
+}
    • addedInput schema / properties / offset
      Added value: +{
+  "description": "Strategies to skip (paging).",
+  "minimum": 0,
+  "type": "integer"
+}
  3. Changed2 schema fields changed
    • changedInput schema / properties / verdict / description
      Previous value: -"Filter by verdict. Default 'all'."New value: +"Filter by verdict. Default 'all'. Note 'insufficient_evidence' is NOT the same as 'insufficient_data': the former has enough runs but they disagree (the effect's 90% interval straddles the ±1pp line), the latter simply lacks runs."
    • changedInput schema / properties / verdict / enum
      Previous value: -[
-  "helps",
-  "neutral",
-  "hurts",
-  "insufficient_data",
-  "all"
-]New value: +[
+  "helps",
+  "neutral",
+  "hurts",
+  "insufficient_evidence",
+  "insufficient_data",
+  "all"
+]
  4. Changed2 schema fields changed
    • changedInput schema / properties / market / description
      Previous value: -"Asset class to analyze (crypto only)."New value: +"Market to analyze (crypto or tokenized)."
    • changedInput schema / properties / market / enum
      Previous value: -[
-  "crypto"
-]New value: +[
+  "crypto",
+  "tokenized"
+]
  5. Changed2 schema fields changed
    • changedInput schema / properties / market / description
      Previous value: -"Asset class to analyze."New value: +"Asset class to analyze (crypto only)."
    • changedInput schema / properties / market / enum
      Previous value: -[
-  "crypto",
-  "stocks",
-  "etf",
-  "commodities",
-  "forex"
-]New value: +[
+  "crypto"
+]
  6. First observed

TDQS

A4.4/5.0
Behavior5/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does this exceptionally well: explains the non-trivial delta_cagr computation, the bootstrap-based verdict logic, the gating and null reasons, the response structure, pagination behavior, and even that filters are evaluated in isolation with net vs gross distinction. Nothing is hidden; the tool's quirks (e.g., delta differs from filtered−baseline) are transparent.

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 every sentence carries substantive information needed for correct invocation given the tool's complexity and lack of output schema. It front-loads the core question and then cascades into details logically. While it could be restructured with sections, it avoids fluff and repetition. The length is justified by the information density.

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 5 parameters, no output schema, and complex gating/grouping behavior, the description is thoroughly complete. It explains the response envelope, per-strategy blocks, folding of empty cells, pagination with truncation, and the free-tier note. An agent has everything needed to call the tool correctly and interpret results without additional schemas.

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 the baseline is 3. The description goes further by explaining the verdict parameter's nuanced meanings (already partially in schema but reinforced), the paging semantics (strategies per page), and how the strategy param restricts to a single key. It adds context about the response grouping that clarifies parameter effects, though some concrete param guidance (e.g., exact values for market) is already in schema.

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 clear question and then states the tool's purpose precisely: 'Platform-wide aggregated analysis: how each Pro+ entry filter affects strategy CAGR'. It mentions specific filter names and the exact metric (delta_cagr) and distinguishes its aggregated, platform-wide scope from the many sibling get_* tools that are per-strategy or narrower. The verb 'get edge reports' is clear and the description leaves no ambiguity about what resource is returned.

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?

The description gives detailed context about the tool's aggregation semantics, gating rules, and response grouping, but it never explicitly says when to choose this tool over alternatives like arena_get_strategy_filter_effect or arena_get_filter_insights. It implies it is the platform-wide edge analysis, but does not name alternatives or exclusion criteria. An agent would need to infer the differentiation.

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