Skip to main content
Glama

Backtesting Arena

by io.github.Schoasch
OverviewDiscussionsAdmin

Get Strategy Insights Matrix or Detail

arena_get_strategy_insights

Which strategy and interval combinations actually performed? Aggregated backtest performance per (strategy × interval) cell. If strategy AND interval provided, returns detail with per-asset breakdown + param variants. Otherwise returns the matrix. Free tier is limited to the same strategies that are free in the backtester itself (rsi_sma, golden_cross, rsi_ob_os, bnh_fixed, dca_reference, dca_reference_v2); the response then carries plan_capped: true plus plan_cap_note, so a short matrix is never mistaken for a thin database. Detail mode on a Pro-only strategy returns 403 rather than a silently empty answer. API Pro and Power receive every cell. Counts: runCount = deduplicated runs above the trade floor that carry the averages, inertRuns = 0-trade runs of the same cell counted IN ADDITION, runs_total = both. avgWinRate averages only runs with a rated trade (0-trade runs and open single positions store 0, which is not a hit rate); avgBuyholdCagr/beatsBuyhold are shown only when >= 50 % of the cell's assets carry the strategy-window benchmark (bhAssetCoverage) — the envelope carries benchmark_definition, win_rate_definition and counts_definition. Matrix mode also carries summary (cells_total, cells_with_benchmark, cells_beating_bh, cells_beating_bh_with_negative_cagr, cells_without_cagr) counted over the cells actually returned — quote those instead of counting cells yourself. [Free: 6 strategies / Pro+: full]

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
intervalNoDetail mode: interval. Candle interval: '1d' daily, '2d'/'3d' multi-day, '1w' weekly, '1M' monthly. Multi-day candles (2d/3d) are anchored to the Unix epoch, so one of n possible alignments is used. Measured on our own corpus, the choice of alignment alone moves CAGR by 6.66 pp on average (max 12.30). Treat differences below that as not distinguishable — 1d/2d/3d behaved as one block in our tests, not a ranking.
min_runsNoMatrix mode: minimum runs per cell. Default 5.
strategyNoDetail mode: strategy key (used together with `interval`).
asset_typeNoRestrict to one asset class.
assets_modeNo'top10' restricts to top-10 pairs by run-count.
ref_strategyNoBenchmark reference. Default 'bh'.

Schema Changelog

Changes observed during successful MCP inspections.

  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"
-}
    • removedInput schema / required
      Removed value: -[
-  "context"
-]
  2. Changed1 schema field changed
    • changedInput schema / properties / interval / description
      Previous value: -"Detail mode: interval."New value: +"Detail mode: interval. Candle interval: '1d' daily, '2d'/'3d' multi-day, '1w' weekly, '1M' monthly. Multi-day candles (2d/3d) are anchored to the Unix epoch, so one of n possible alignments is used. Measured on our own corpus, the choice of alignment alone moves CAGR by 6.66 pp on average (max 12.30). Treat differences below that as not distinguishable — 1d/2d/3d behaved as one block in our tests, not a ranking."
  3. Changed1 schema field changed
    • changedInput schema / properties / interval / enum
      Previous value: -[
-  "1d",
-  "1w",
-  "1M"
-]New value: +[
+  "1d",
+  "2d",
+  "3d",
+  "1w",
+  "1M"
+]
  4. Changed1 schema field changed
    • changedInput schema / properties / asset_type / enum
      Previous value: -[
-  "crypto"
-]New value: +[
+  "crypto",
+  "tokenized_equity",
+  "tokenized_etf",
+  "commodities"
+]
  5. Changed1 schema field changed
    • changedInput schema / properties / asset_type / enum
      Previous value: -[
-  "crypto",
-  "stock",
-  "etf",
-  "commodities",
-  "forex"
-]New value: +[
+  "crypto"
+]
  6. First observed

TDQS

A4.3/5.0
Behavior5/5

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

With no annotations present, the description carries the full behavioral burden and does so: free-tier strategy caps plus `plan_capped`/`plan_cap_note`, 403 rather than silent empty detail on Pro-only strategies, and precise definitions for `runCount`/`inertRuns`/`runs_total` and `avgWinRate`. It also discloses the >=50% `bhAssetCoverage` gate before benchmark fields are shown, which is exactly the kind of non-obvious behavior an agent needs.

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 long, but front-loaded with the purpose and mode logic before the definitional detail, and each clause (counts, win-rate definition, benchmark gate, free tier) earns its place given there is no output schema. Slightly dense for a single paragraph.

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 complex, zero-annotation, no-output-schema tool, the description covers mode selection, error behavior, tier limits, return-field semantics and the embedded definition envelope. An agent has everything needed to call it correctly and interpret the response without guessing.

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, but the description adds mode semantics the schema does not: `strategy`+`interval` jointly select detail mode, `min_runs` is matrix-only, and it names the free strategies explicitly. The `ref_strategy`, `asset_type` and `assets_mode` params get no added meaning beyond the schema.

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 opening question and the phrase 'Aggregated backtest performance per (strategy × interval) cell' give a specific verb and resource, and the matrix/detail duality is spelled out. It does not, however, explicitly differentiate itself from close siblings such as arena_get_strategy_performance or arena_compare_strategies, so an agent must infer the split from the schema shape.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Routing is well specified internally: supplying both `strategy` and `interval` yields detail (with a 403 for Pro-only strategies), otherwise the matrix, and `min_runs` is scoped to matrix mode. There is no guidance on when to prefer this over the sibling performance/compare tools, which keeps it below 5.

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