Skip to main content
Glama
janorium-mcp

janorium-mcp

Official

Analog Lab query

analogs_query

Query historical market analogs to compute forward-return quantile fans, event studies, and trade-plan flags for crypto strategy validation.

Instructions

POST /analogs/query per docs://analog-query-reference: the forward-return quantile fan of historical states like the anchor, the event study, the trade plan and flags. Long series are trimmed to their head. Inside a campaign the anchor must be {mode:"AT", ts} with ts + horizon before the locked region.

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": "analogs_query"
  }
}

Input Schema

NameRequiredDescriptionDefault
requestYesAnalogQueryRequest (docs://analog-query-reference).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3/5.0
Behavior4/5

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

Annotations declare a non-read-only, non-destructive, non-idempotent POST, so the agent already knows this is a computation with no side effects on stored data. The description adds real behavior beyond that: long series are trimmed to their head (silent truncation) and there is a hard campaign precondition on anchor shape and horizon placement. It is not just restating annotations.

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

Conciseness3/5

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

It is compact and front-loads the endpoint and doc reference, but the prose is dense with unexplained domain jargon ('quantile fan', 'historical states like the anchor', 'locked region') and the docs:// pointer takes space a self-contained sentence would serve better.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given a nested, undocumented request object and no output schema, naming the returned artifacts helps orient the agent. However, the description outsources the request contract to an external document and says nothing about response shape, error modes, or cost, leaving meaningful gaps for a complex analytic tool.

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?

Only one parameter (request) exists, and the schema is an opaque additionalProperties object, so the 100% 'coverage' carries almost no real information. The description partially compensates by specifying the anchor shape {mode:"AT", ts} inside a campaign, but the rest of the request body is deferred entirely to the external reference doc.

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

Purpose3/5

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

The description names outputs (forward-return quantile fan, event study, trade plan, flags) over historical states matching an anchor, which conveys roughly what the call produces. But the operation is expressed as an HTTP route plus a doc pointer rather than a clear verb+resource statement, and the core notion of an 'analog' is never defined, leaving the purpose somewhat vague.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is one genuine usage constraint: inside a campaign the anchor must be {mode:"AT", ts} with ts + horizon before the locked region. Beyond that, nothing says when to use this tool versus alternatives (e.g. backtest_* siblings) or when it is inappropriate.

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