Skip to main content
Glama
janorium-mcp

janorium-mcp

Official

Dry-run a strategy config

strategy_dry_run

Simulate a saved strategy with config overrides once without saving, returning run metrics, exits, per-layer blockers, and optional explain or randomized-entry analysis.

Instructions

Runs a config once without saving anything. strategyId is the saved base strategy (ownership); config overrides its saved config. Without explain/randomizedEntry: synchronous, returns the full RunSummary (metrics, exits, per-layer fired/opened/blockedBy and top blockers, inertFeatures). With explain or randomizedEntry: asynchronous, returns {dryRunId, kind:"DRY_RUN"} — then call wait {kind:"DRY_RUN", ids:[dryRunId]}.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "strategyId": "<strategyId>",
      "from": "<from>",
      "to": "<to>"
    },
    "name": "strategy_dry_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
toYesISO-8601 instant, or a date `YYYY-MM-DD` read as 00:00 UTC.
fromYesISO-8601 instant, or a date `YYYY-MM-DD` read as 00:00 UTC. Limits: from on or after 2020-01-01, to at most 24 h past now, from before to, at most 500,000 bars per run (422 PERIOD_TOO_EARLY / INVALID_PERIOD / PERIOD_TOO_LONG otherwise).
configNo
symbolNoDefaults to config.instrument.symbol.
explainNoCondition trace; true = the recent end of the period.
exchangeNoDefaults to config.market.exchange, then binance.
leverageNoFutures only. Defaults to config.market.futures.leverage.
timeframeNoDefaults to config.instrument.timeframe.
marginModeNo
marketTypeNoDefaults to config.market.type.
strategyIdYes
applyFundingNo
initialCapitalNoDefaults to 10000.
randomizedEntryNoNull-model comparison: the same exits and sizing with coin-flip entries.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description discloses the two execution modes and the exact return shapes for each, including that the synchronous path yields a full RunSummary with metrics, exits, per-layer counts and inertFeatures. It also closes the async loop by naming the required wait call, which no annotation or schema field conveys.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The persistence constraint is front-loaded, parameter semantics come second, and the sync/async return behavior closes it out. Every clause carries operational information for a complex tool, and the parenthetical enumeration of RunSummary fields is compact rather than verbose.

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 14-parameter tool with a nested config object, the description covers the essentials an agent needs to call it correctly: what gets persisted (nothing), which params drive mode selection, and how to complete the async path. Gaps are minor, such as what happens to the dryRunId record afterwards and how long it remains resolvable via wait.

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 71%, so the schema already documents from/to limits, defaults and enums; the description still adds real meaning by defining strategyId as the saved base strategy and config as an override of that saved config, resolving the main ambiguity in a 14-parameter tool. It does not explain randomizedEntry as a null-model (the schema does) and says nothing extra about exchange/timeframe/marginMode fallbacks.

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?

"Runs a config once without saving anything" names a concrete verb and resource plus the key scope constraint (no persistence), which separates it from strategy_save and from a real backtest_run. It also defines the relationship between strategyId (ownership) and config (override), so an agent understands the tool's model before opening the 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?

It clearly routes the agent: without explain/randomizedEntry use it synchronously, with either of those it returns {dryRunId, kind:"DRY_RUN"} and the agent must follow up with wait {kind:"DRY_RUN", ids:[dryRunId]}. What is missing is explicit guidance on when to prefer this over backtest_run/strategy_validate, but the sync-vs-async branching is a strong, actionable condition.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.