Skip to main content
Glama

Backtesting Arena

by io.github.Schoasch
OverviewDiscussionsAdmin

List Available Trading Strategies

arena_list_strategies

Which strategies can I backtest here? Lists all backtest strategies (key, label, plan, supported asset classes, primary indicators). Filterable by asset class and plan. Use this before calling arena_run_backtest to discover valid strategy names. Entries deprecated for an asset class stay listed (historical results depend on them) and carry deprecated_for + deprecation {since, reason} — do NOT call arena_run_backtest or validate_strategy for those combinations, they return 400. [Free tier]

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
langNoLocalized names/taglines. Default 'en'.
planNoFilter to strategies of this plan tier.
asset_classNoFilter to strategies supporting this asset class (crypto or tokenized_rwa).

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. Changed2 schema fields changed
    • changedInput schema / properties / asset_class / description
      Previous value: -"Filter to strategies supporting this asset class (crypto only)."New value: +"Filter to strategies supporting this asset class (crypto or tokenized_rwa)."
    • changedInput schema / properties / asset_class / enum
      Previous value: -[
-  "crypto"
-]New value: +[
+  "crypto",
+  "tokenized_rwa"
+]
  3. Changed2 schema fields changed
    • changedInput schema / properties / asset_class / description
      Previous value: -"Filter to strategies supporting this asset class."New value: +"Filter to strategies supporting this asset class (crypto only)."
    • changedInput schema / properties / asset_class / enum
      Previous value: -[
-  "crypto",
-  "stock",
-  "etf",
-  "commodities",
-  "forex"
-]New value: +[
+  "crypto"
+]
  4. First observed

TDQS

A4.3/5.0
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. It discloses that deprecated entries intentionally stay listed, that they carry deprecated_for and deprecation metadata, and that invalid combinations fail with 400. This exposes important non-obvious behavior. It doesn't mention response shape, pagination, or auth, but the key traps are covered.

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 compact and front-loaded with a natural question, then the core behavior, then the critical deprecation caveat. The deprecation sentence is long but packs essential warning details. Overall it earns its place without unnecessary fluff.

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?

For a simple optional-parameter list tool with no output schema, the description covers what the tool returns, what filters exist, how it relates to arena_run_backtest, and the important deprecation edge case. A small example of output shape or a note about lang default would push it higher, but nothing critical is missing.

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. The description adds only minimal parameter semantics by mentioning filterability by asset class and plan; it doesn't add new meaning for lang or any details beyond the schema. No penalty is warranted because the schema already documents each parameter well.

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 starts with a concrete user question and states the exact function: 'Lists all backtest strategies' with the specific fields returned (key, label, plan, supported asset classes, primary indicators). It also frames itself as a discovery tool for arena_run_backtest, which distinguishes it from the many other list/get tools in its sibling set.

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?

Usage guidance is explicit: 'Use this before calling arena_run_backtest to discover valid strategy names.' It also gives a clear negative directive — do not call arena_run_backtest or validate_strategy for deprecated asset-class combinations, and states the consequence (they return 400). This is strong, unambiguous routing.

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