Skip to main content
Glama

Backtesting Arena

by io.github.Schoasch

Run Backtest on a Pair Universe (async)

arena_run_universe_backtest

Does this strategy hold up across a whole universe? Runs it against every pair in the universe. Pair cap depends on your API tier: Pro 50, Power 250 — Power covers crypto-top-250 in ONE job, and a single job keeps the ranking on one pair set (merging results across different pair sets measures pair selection, not strategy quality). THIS CALL IS ASYNCHRONOUS AND RETURNS NOTHING BUT A job_id: the result is NOT in this response. You MUST poll arena_get_job_status until status is 'completed'; estimated_seconds in the create-response says how long to budget. Provide either universe_id (call arena_list_universes) OR explicit pairs[]. Benchmarks bnh_fixed and dca_reference are accepted here — run one of them over the SAME universe and interval alongside: an excess over buy-and-hold is only readable next to the buy-and-hold value itself, which can be negative. beats_bh_count compares each pair's cagr against the LIKE-FOR-LIKE buy-and-hold — the benchmark measured over the window the strategy actually traded, not from the requested start. A long warmup or a pair listed after date_from shifts that start, and comparing across two different windows is a handicap, not a benchmark. The old pairing is still reported as beats_bh_count_requested_window, and pairs_with_window_offset says on how many pairs the two can differ at all; per-pair, buyhold_cagr_strategy_window and benchmark_matches_window carry the same distinction. PERSISTENCE: universe results live ONLY in the job response (api_jobs.result). They are deliberately not written to backtest_runs, so they carry no filter_binding and no coin-denominated history, and you will not find them later via arena_list_backtests — copy what you need out of the job result. Per-day quota: Pro=5, Power=50. [API Pro tier]

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pairsNoExplicit pair list. Hard schema limit 250; the effective cap is your tier (Pro 50, Power 250). Use instead of universe_id.
paramsNoStrategy-specific parameters applied to EVERY pair in the universe. Omit for audited defaults.
capitalNoStarting capital in quote currency. Default 10000. Affects absolute figures only, not CAGR or win-rate.
date_toNoEnd date, YYYY-MM-DD. Default: today.
filtersNoOptional entry filters (Pro+). Each one only ever REMOVES entries — filters never create trades. Omit for the unfiltered baseline.
intervalYesCandle 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.
strategyYesStrategy key — call arena_list_strategies.
date_fromYesStart date, YYYY-MM-DD. Earlier than the pair listing is clamped to the first available candle.
universe_idNoPre-curated universe — call arena_list_universes for valid IDs. Capped by tier (Pro 50, Power 250); a larger universe is rejected rather than silently truncated.

Schema Changelog

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

  1. Changed1 schema field changed
    • addedInput schema / properties / filters / properties / stochRsiWeekly
      Added value: +{
+  "description": "Asset-specific weekly Stoch-RSI gate: entries only while the pair's weekly StochRSI(14) sits above its SMA(3). Default false.",
+  "type": "boolean"
+}
  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: -[
-  "strategy",
-  "interval",
-  "date_from",
-  "context"
-]New value: +[
+  "strategy",
+  "interval",
+  "date_from"
+]
  3. Changed3 schema fields changed
    • changedInput schema / properties / pairs / description
      Previous value: -"Explicit pair list (max 50). Use instead of universe_id."New value: +"Explicit pair list. Hard schema limit 250; the effective cap is your tier (Pro 50, Power 250). Use instead of universe_id."
    • changedInput schema / properties / pairs / maxItems
      Previous value: -50New value: +250
    • changedInput schema / properties / universe_id / description
      Previous value: -"Pre-curated universe — call arena_list_universes for valid IDs. Max 50 pairs."New value: +"Pre-curated universe — call arena_list_universes for valid IDs. Capped by tier (Pro 50, Power 250); a larger universe is rejected rather than silently truncated."
  4. Changed2 schema fields changed
    • changedInput schema / properties / interval / description
      Previous value: -"Candle interval: '1d' daily, '1w' weekly, '1M' monthly."New value: +"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."
    • changedInput schema / properties / interval / enum
      Previous value: -[
-  "1d",
-  "1w",
-  "1M"
-]New value: +[
+  "1d",
+  "2d",
+  "3d",
+  "1w",
+  "1M"
+]
  5. Changed11 schema fields changed
    • addedInput schema / properties / capital / description
      Added value: +"Starting capital in quote currency. Default 10000. Affects absolute figures only, not CAGR or win-rate."
    • addedInput schema / properties / date_from / description
      Added value: +"Start date, YYYY-MM-DD. Earlier than the pair listing is clamped to the first available candle."
    • addedInput schema / properties / date_to / description
      Added value: +"End date, YYYY-MM-DD. Default: today."
    • addedInput schema / properties / filters / description
      Added value: +"Optional entry filters (Pro+). Each one only ever REMOVES entries — filters never create trades. Omit for the unfiltered baseline."
    • addedInput schema / properties / filters / properties / altcoinSeasonMode / description
      Added value: +"Altcoin-Season gate. 'conservative' needs a confirmed alt season, 'aggressive' an early one. Default 'off'."
    • addedInput schema / properties / filters / properties / atrMode / description
      Added value: +"ATR volatility regime filter. 'low'/'high' restrict entries to that volatility band, 'expansion' to rising volatility. Default 'off'."
    • addedInput schema / properties / filters / properties / bullmarketStageMode / description
      Added value: +"Bull-market stage gate from the BTC cycle model; rising strictness from 'early' to 'strict'. Default 'off'."
    • changedInput schema / properties / filters / properties / minProfitGuardThreshold / description
      Previous value: -"Per-trade min profit guard (negative cap, e.g. -10)."New value: +"Per-trade min profit guard (negative cap, e.g. -10 = exit once a trade is 10% under water)."
    • changedInput schema / properties / filters / properties / wma200 / description
      Previous value: -"200-week MA filter (BTC-derived)."New value: +"200-week MA filter (BTC-derived): only take entries while BTC trades above its 200-week SMA."
    • addedInput schema / properties / interval / description
      Added value: +"Candle interval: '1d' daily, '1w' weekly, '1M' monthly."
    • addedInput schema / properties / params / description
      Added value: +"Strategy-specific parameters applied to EVERY pair in the universe. Omit for audited defaults."
  6. First observed

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations provided, the description carries the full disclosure burden and does so thoroughly: it exposes async result handling, tier-based pair caps, per-day quota, non-persistence of results, benchmark window offsets, and the distinction between strategy-window and requested-window comparisons. No major behavioral surprise is left hidden.

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 dense and mostly earns its length. It front-loads the async warning, pair cap, and persistence caveats, which are the most critical operational facts. It loses one point because the benchmark-window discussion is quite heavy and could be tightened without losing meaning.

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 an async tool with no output schema, the description is remarkably complete: it explains what the response contains (job_id), how to get the actual result, what to copy, how benchmarking should be structured, what the benchmark fields mean, and how quota and tier constraints apply. An agent has enough information to call it correctly and interpret the outcome safely.

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 useful parameter-level context beyond the schema: valid benchmark strategy keys (bnh_fixed, dca_reference), the either/or relationship between universe_id and pairs, the tier-based cap behavior, and the fact that results only exist transiently in the job response. This goes beyond what the schema already documents.

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 use-case question and states a specific verb and resource: it runs the given strategy against every pair in the universe. It immediately distinguishes itself from single-pair runs and retrieval tools by emphasizing the async contract (returns only a job_id), and it is clearly differentiated from siblings like arena_run_backtest and arena_get_job_status.

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 gives an explicit workflow: poll arena_get_job_status until completed, provide either universe_id (via arena_list_universes) or explicit pairs[], and run benchmarks over the same universe and interval. It also warns that results are not discoverable via arena_list_backtests, which tells the agent exactly where to look and where not to look.

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