Skip to main content
Glama
janorium-mcp

janorium-mcp

Official

Promote a variant

optimization_promote
Destructive

Promotes the selected optimization variant to a new strategy version and launches an out-of-sample backtest when an OOS window exists, while protecting campaign holdouts from premature use.

Instructions

Writes the variant as a new version of the source strategy and, when the run has an OOS window, launches the OOS backtest. Returns {promotedStrategyVersion, oosBacktestId}. Inside a campaign an OOS window in the locked region is refused — the holdout is spent only by campaign_finalize.

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": {
      "runId": "<runId>",
      "variantIdx": "<variantIdx>"
    },
    "name": "optimization_promote"
  }
}

Input Schema

NameRequiredDescriptionDefault
runIdYes
variantIdxYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and idempotentHint=false, and the description adds real context beyond them: the write creates a new strategy version, a side-effect backtest may be spawned, the exact refusal condition inside campaigns, and the shape of the return value. It never explains what the destructive aspect actually touches, e.g. whether a prior promoted version is replaced, which is the one meaningful behavioral gap.

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?

Three sentences: the action first, the return value second, the campaign restriction last. Nothing is redundant and the conditional behavior is front-loaded rather than buried.

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 destructive two-parameter mutation with annotations covering the safety profile, the definition covers the action, conditional side effect, return fields (no output schema exists, so this matters), and an important refusal case. The only material shortfall is parameter explanation, which is left at zero coverage.

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

Parameters2/5

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

Schema description coverage is 0% for both parameters, so the description must carry the load, but it only gestures at them via the words 'the run' and 'the variant'. It never clarifies that variantIdx is a zero-based index into the run's variant list (its minimum is 0) or what runId refers to, leaving the agent to infer both.

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 names a specific verb and resource: it writes a variant into a new version of the source strategy and conditionally launches an OOS backtest. It also states the concrete return fields, so an agent knows exactly what the call produces and can distinguish it from read-only siblings like optimization_get.

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 gives a clear conditional rule for the OOS backtest ('when the run has an OOS window') and an explicit exclusion ('Inside a campaign an OOS window in the locked region is refused'), pointing to campaign_finalize as the path that actually spends the holdout. It does not state the prerequisite that a run and variants must already exist, which keeps it from a 5.

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