Skip to main content
Glama
Sign In

aipricepatterns

by com.aipricepatterns
OverviewDiscussionsAdmin

Replay a Price-Level Hypothesis

replay_candle_hypothesis
Read-onlyIdempotent

Replay one already stated price hypothesis as round trips. Entry is the level, and only after a candle opens on the near side and trades through it. A candle that opens through the level is an unfilled gap. Exit is the target, the invalidation, or the final close if the horizon ends. Both prices in one candle stay unknown and are left out of the sum. feePctPerSide defaults to 0.1 percent and is charged on entry and exit. The clock still starts at the anchor. Under 10 touches the verdict is INSUFFICIENT_DATA. Returns NO_TRADE. This is not a win rate, a search over stops, or a replacement for RLXBT.

Input Schema

NameRequiredDescriptionDefault
fNoHorizon in bars, counted from the anchor. Default 10
qNoPattern length preset. Default 5
symbolNoBTCUSDT, ETHUSDT or SOLUSDT. Default BTCUSDT
anchorTsNoOptional historical snapshot time in Unix milliseconds
intervalNoChart timeframe. Default 1h
levelPriceYesEntry level the caller named. Required. Do not invent it from a band.
targetPriceYesPrice beyond the level that closes the round trip as a target
feePctPerSideNoPercent of notional charged on entry and again on exit. Default 0.1
invalidationPriceYesPrice on the other side of the level that closes the round trip as an invalidation

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / levelPrice / description
      Previous value: -"Entry level. The trade exists only after price trades through this level. Default is the neighbour P90 above the close"New value: +"Entry level the caller named. Required. Do not invent it from a band."
    • changedInput schema / required
      Previous value: -[
-  "targetPrice",
-  "invalidationPrice"
-]New value: +[
+  "levelPrice",
+  "targetPrice",
+  "invalidationPrice"
+]
  2. Added

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already cover read-only and idempotent, and the description goes well beyond them: fees charged on both sides, gap candles that open through the level counting as unfilled, ambiguous two-price candles excluded from the sum, and the ten-touch INSUFFICIENT_DATA / NO_TRADE verdict thresholds. What it does not disclose is the shape of the round-trip output, which matters since there is no output schema.

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?

The core mechanic is front-loaded in the first two sentences and every sentence carries rules rather than filler. The telegraphic fragments ("Both prices in one candle stay unknown and are left out of the sum") are terse to the point of being slightly cryptic, but nothing is redundant.

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 nine-parameter simulation with no output schema, the description covers the mechanics an agent needs to call it sensibly: fill conditions, exit rules, cost model, and minimum-sample verdict. It leaves unanswered what a successful result contains (per-trip list vs. aggregate) and what the q pattern-length preset changes, which are the remaining gaps.

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?

Schema coverage is 100%, so all nine parameters are already documented, and the description mostly restates them (fee default, entry level, target and invalidation as exit conditions). The one genuine addition is "the clock still starts at the anchor," which clarifies that anchorTs governs horizon counting even on replay. That is marginal value over the schema, so baseline 3 fits.

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?

"Replay one already stated price hypothesis as round trips" names a specific verb and resource, and the following sentences pin down entry, exit, and fill rules. It does not explicitly differentiate itself from the near-identically named siblings evaluate_candle_hypothesis or investigate_candle_event_hypothesis, so an agent must infer the boundary.

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 states the key precondition (the hypothesis must already be stated, levelPrice must not be invented from a band) and three negative exclusions: not a win rate, not a stop search, not a replacement for RLXBT. It stops short of naming which sibling to use for those adjacent jobs, leaving the routing partly implicit.

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

All aipricepatterns toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources