Skip to main content
Glama
janorium-mcp

janorium-mcp

Official

Why entries did not happen

backtest_near_miss
Read-onlyIdempotent

Analyze near-miss bars for one entry layer: report evaluated, fired, and opened counts, plus how often each condition blocked or was false; run engine-backed re-runs sequentially.

Instructions

For one entry layer: bars evaluated/fired/opened, near-miss bars (all conditions but tolerance held) and, per top-level condition, how often it was the one blocking (blockingPct) and how often it was false at all (falsePct). Layer defaults to the first. Condition labels are «untrusted:…» text built from the config. Engine-backed: at most 2 such re-runs per user at a time — call these one after another, not in parallel.

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": {
      "backtestId": "<backtestId>"
    },
    "name": "backtest_near_miss"
  }
}

Input Schema

NameRequiredDescriptionDefault
layerNo
toleranceNo
backtestIdYes

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?

Annotations already cover read-only/idempotent/non-destructive/closed-world, yet the description adds critical operational behavior: engine-backed re-runs are capped at 2 per user, so calls must be serialized. It also warns that condition labels are «untrusted:…» text derived from config, which flags a prompt-injection risk an agent would otherwise not anticipate.

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?

Roughly three sentences, all carrying load, with the operational warning placed last where it reads naturally before invocation. The opening sentence is dense — metric names, a parenthetical definition, and camelCase field labels packed together — but nothing is redundant.

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

Completeness5/5

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

There is no output schema, and the description compensates fully by describing the returned metrics and their meaning. Combined with the defaulting rule, the untrusted-label caveat, and the concurrency limit, an agent has everything needed to call and interpret this tool correctly.

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 0%, so the description must carry parameter meaning. It explains `layer`'s default (first layer) and defines `tolerance` functionally as the condition whose violation defines a near-miss. `backtestId` is left implicit but is self-evident as the required target identifier; the 0–3 range of tolerance is left to 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?

The description names a specific resource (one entry layer's diagnostic breakdown) and enumerates exactly what the output contains: bars evaluated/fired/opened, near-miss bars where only `tolerance` held, and per-condition blockingPct/falsePct. This clearly separates it from siblings like backtest_get or backtest_signals, which would not report condition-level blocking attribution.

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 concrete context: use it for one entry layer, and layer defaults to the first when unspecified, so an agent knows how to call it without extra input. The sequential-call constraint (not in parallel) is explicit. It does not name a competing sibling for related diagnostics, 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.