Skip to main content
Glama
janorium-mcp

janorium-mcp

Official

Start a campaign (reserve the holdout)

campaign_start
Destructive

Starts a backtest campaign by setting its period and locking a holdout segment; every run and read is refused inside that window until finalization.

Instructions

Declares the period and reserves its tail as a holdout before anything is run. holdoutFrom must leave at least half of [from, to] in-sample. From then on every run and every read whose period reaches [holdoutFrom − embargo, to] is refused with HOLDOUT_LOCKED; embargo = max(maxHoldingBars, 24) bars. Every attempt becomes a ledger row (campaign://{id}/ledger); the holdout is run once, by campaign_finalize. A campaign over a period an earlier campaign already covered inherits its trial count; a holdout another campaign already spent is refused (HOLDOUT_SPENT).

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": {
      "name": "<name>",
      "symbols": "<symbols>",
      "timeframes": "<timeframes>",
      "from": "<from>",
      "to": "<to>",
      "holdoutFrom": "<holdoutFrom>"
    },
    "name": "campaign_start"
  }
}

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.
nameYes
symbolsYesThe holdout is run on symbols × timeframes (≤ 30); DSR uses the first pair.
strategyIdNoThe strategy the campaign is about, for the ledger header.
timeframesYes
holdoutFromYesISO-8601 instant, or a date `YYYY-MM-DD` read as 00:00 UTC.
parentCampaignIdNoInherit the trial count of this campaign. Detected automatically when the periods overlap.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the annotations (destructiveHint=true, idempotentHint=false), the description discloses the lock window [holdoutFrom − embargo, to], how embargo is computed (max(maxHoldingBars, 24) bars), that every attempt writes a ledger row, that the holdout is single-use and consumed by campaign_finalize, and that trial counts are inherited on overlapping periods. This is exactly the kind of consequence-of-calling detail annotations cannot carry.

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?

Four tight sentences, no filler, with the core action and its constraint front-loaded before the failure modes. Density of domain jargon (embargo, DSR, holdout) makes it slower to parse than necessary, but every sentence carries information an agent needs.

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, non-idempotent 8-parameter mutation with no output schema, the description covers locking, ledger side effects, refusal codes, and trial inheritance. The one gap is that it never says what a successful call returns — presumably a campaign id, which the ledger URI references — leaving the agent to infer it.

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 75%, and the description adds a real constraint not present in the schema: holdoutFrom must leave at least half of [from, to] in-sample. It also ties holdoutFrom to the embargo window. It says nothing extra about name, timeframes, or strategyId, but those are adequately documented in the schema.

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?

States a concrete verb and resource — 'Declares the period and reserves its tail as a holdout' — and implicitly contrasts with campaign_finalize, which it names as the tool that actually runs the holdout. An agent can distinguish this creation step from the finalize step without opening either 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 timing is explicit: this must happen 'before anything is run', and the description routes the run step to campaign_finalize. It also gives the refusal conditions (HOLDOUT_LOCKED, HOLDOUT_SPENT) that tell the agent when this call will fail, though it doesn't spell out the prerequisite call sequence or what to do on refusal.

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