Skip to main content
Glama
janorium-mcp

janorium-mcp

Official

Start an optimizer run

optimization_create

Creates a crypto strategy optimization run from a search space, scoring, and window spec, returning a run ID to monitor.

Instructions

POST /optimizations with a body exactly as docs://optimizer-run-reference describes (searchSpace, windowSpec, scoring). Returns {runId}; then wait {kind:"OPTIMIZATION"}. At most 2 active runs per user. Inside a campaign windowSpec (optimize window and any oosFrom/oosTo) must end before the locked region, and every variant becomes a ledger trial.

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": {
      "request": "<request>"
    },
    "name": "optimization_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
requestYesCreateOptimizationRequest (docs://optimizer-run-reference).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior5/5

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

Beyond the annotations (write, non-idempotent, non-destructive), it discloses a hard quota of 2 active runs per user, the returned {runId} payload, and a non-obvious side effect — every variant becomes a ledger trial. Those are exactly the operational facts an agent cannot infer from the annotation set.

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?

All four sentences carry real content (body, return, chaining, quota, campaign constraint) with no filler. The second half runs together return value, follow-up call, quota, and window rules in one dense stretch, which slightly hurts scannability.

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 supplies the return shape and the follow-up call, and it covers the nested request object's key sections. The only gap is that the authoritative field semantics live in an external document rather than the definition, which is acceptable but leaves the agent dependent on that reference.

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 100% but the single 'request' parameter is an opaque additionalProperties object, so the schema itself conveys no field meaning. The description compensates by naming the required body sections (searchSpace, windowSpec, scoring) and pointing to docs://optimizer-run-reference, though field-level semantics remain external.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

It states a concrete verb and resource ('POST /optimizations', 'Start an optimizer run') and names the request body shape, so an agent can tell it apart from optimization_get or optimization_promote. Specificity of what the run does (search space over a window) is delegated to an external doc reference rather than stated here, which keeps it just short of a 5.

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 gives a clear workflow: create the run, then call wait with {kind:"OPTIMIZATION"}, and it states preconditions (max 2 active runs, campaign window must end before the locked region). It doesn't name alternatives for checking or promoting a run, so exclusions are absent, but the usage context is unambiguous.

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