Skip to main content
Glama

Backtesting Arena

by io.github.Schoasch

Dip Scenario — structural tranche ladder + base rate

arena_dip_scenario

Where would I add on a dip, and when is the thesis wrong? Turn a dip/accumulation thesis into a concrete, checkable plan from YOUR assumptions. Given an asset (BTC/ETH/SOL), a named cycle-state preset and a thesis horizon, returns: (1) a tranche LADDER anchored to STRUCTURAL marks (200-week MA, support clusters) below spot — marks the market has actually traded at, rather than calendar dates; (2) the cited historical base rate from the analog engine (what forward returns followed comparable states, with episodes_matched and sample size); (3) the explicit lump-sum-vs-tranche tradeoff (laddering buys lower timing variance; expected value stays with the base rate). Requires an invalidation point (mandatory: at what scenario is the thesis wrong). Composes the historical-analog + key-levels tools. This structural framing is MCP-only; a related (different-method, EV/Kelly) interactive tool is at https://tradingstrategies.work/analyse/dip-decision. [API Pro tier]

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
assetNoWhich asset. Support-cluster rungs are BTC-only; ETH/SOL use the 200-week MA as the structural mark.BTC
presetYesCycle-state preset for the base rate. One of: cycle_bottom_cluster, cycle_top_cluster, deep_fear, euphoria, quiet_volatility. ETH/SOL: price-derived presets only.
capitalNoOptional total capital — if given, each tranche also returns an absolute amount.
horizon_daysNoThesis horizon in days for the base-rate forward return. Default 180.
invalidationYesMANDATORY: the scenario under which the thesis is wrong (e.g. "weekly close below the 200-week MA"). NOT "where do I buy".
risk_aversionNoLadder tilt. 1 = equal tranches; >1 = weight deeper marks more (more patient); <1 = front-load toward now. Clamped [0.5, 3].

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: -[
-  "preset",
-  "invalidation",
-  "context"
-]New value: +[
+  "preset",
+  "invalidation"
+]
  2. Changed2 schema fields changed
    • changedInput schema / properties / preset / description
      Previous value: -"Cycle-state preset for the base rate. One of: cycle_bottom_cluster, cycle_top_cluster, deep_fear, euphoria. ETH/SOL: price-derived presets only."New value: +"Cycle-state preset for the base rate. One of: cycle_bottom_cluster, cycle_top_cluster, deep_fear, euphoria, quiet_volatility. ETH/SOL: price-derived presets only."
    • changedInput schema / properties / preset / enum
      Previous value: -[
-  "cycle_bottom_cluster",
-  "cycle_top_cluster",
-  "deep_fear",
-  "euphoria"
-]New value: +[
+  "cycle_bottom_cluster",
+  "cycle_top_cluster",
+  "deep_fear",
+  "euphoria",
+  "quiet_volatility"
+]
  3. First observed

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations provided, the description carries the full behavioral burden, and it does substantial work: a mandatory invalidation point, MCP-only availability, API Pro tier gating, composition of two underlying tools, plus the three returned items spelled out. It does not cover rate limits, error behavior, or exact response format, but for a read-only analytical tool this is strong disclosure.

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?

Roughly 140 words for a complex, no-output-schema analytical tool, and nearly all content earns its place: purpose, three enumerated returns, tool composition, sibling disambiguation, and the Pro-tier constraint. It is front-loaded with the core question and reasonably scannable despite being a single paragraph; the light redundancy with the schema's mandatory-invalidation note is defensible for a safety-critical parameter.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description compensates by enumerating the three return components (ladder anchored to structural marks, base rate with episodes_matched and sample size, tranche tradeoff) and the key constraints (mandatory invalidation, BTC-only support clusters, Pro tier). The main gap is the absence of a concrete response shape an agent would need to reliably parse the result.

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

Parameters3/5

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

Schema description coverage is 100%, so the baseline is 3. Every parameter (asset, preset, capital, horizon_days, invalidation, risk_aversion) is already well documented in the schema with enums, defaults, and clamping behavior. The description only reinforces the invalidation requirement without adding new per-parameter semantics beyond what the schema provides.

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 concrete purpose ('Turn a dip/accumulation thesis into a concrete, checkable plan') and enumerates three specific outputs: a structural tranche ladder anchored to actual traded marks, a cited historical base rate, and a lump-sum-vs-tranche tradeoff. It also names the related sibling explicitly ('a related (different-method, EV/Kelly) interactive tool'), so an agent can distinguish it from arena_dip_decision without opening that tool's schema.

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?

The description states it composes the historical-analog and key-levels tools and points to the alternative dip-decision tool, differentiating by method (structural framing vs EV/Kelly). What it stops short of is an explicit when-to-choose rule between this MCP tool and the web alternative — the selection condition is implied by 'different-method' rather than stated as a decision rule.

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