Skip to main content
Glama

aipricepatterns

by com.aipricepatterns
OverviewDiscussionsAdmin

What Is Odd in Candle Memory

what_is_odd_in_candle_memory
Read-onlyIdempotent

Salience card for the current window: coin-flip, neighbour band vs all-history width, ledger coverage vs 80%, closest-twin vs median, era clustering, D tightness. Research bullets, not a trade.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fNoForward horizon in bars. Only the chart presets 5, 10, 30, and 50 are supported
qNoCandles in the matched pattern. Only the chart presets 3, 5, 8, and 12 are supported
limitNoClosest analogues to list (1-20). Bands and direction always use the chart's 20 neighbours
symbolNoSupported chart symbol: BTCUSDT, ETHUSDT, or SOLUSDTBTCUSDT
anchorTsNoOptional historical replay anchor in Unix milliseconds. Omit for the latest chart candle
intervalNoSupported chart timeframe: 5m, 15m, 1h, 4h, or 1d5m
token_idNoOptional Chart access token (64-hex, same as X-Aipp-Chart / the token on /profile). After the daily free MCP quota, paid tools require the Chart $29/mo Stripe subscription. Legacy Manus token_id still works only when MCP_BILLING=manus.
chart_tokenNoOptional Chart access token. Prefer the X-Aipp-Chart header in the MCP client config so every tool call is covered.
includeAnalogueCandlesNoInclude OHLC arrays for every analogue and its continuation. False keeps the response agent-sized

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / limit / description
      Previous value: -"Number of closest candle analogues to return (1-20)"New value: +"Closest analogues to list (1-20). Bands and direction always use the chart's 20 neighbours"
  2. Changed2 schema fields changed
    • addedInput schema / properties / chart_token
      Added value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "anyOf": [
+    {
+      "not": {}
+    },
+    {
+      "minLength": 1,
+      "type": "string"
+    }
+  ],
+  "description": "Optional Chart access token. Prefer the X-Aipp-Chart header in the MCP client config so every tool call is covered."
+}
    • changedInput schema / properties / token_id / description
      Previous value: -"Optional Manus access token. Paid tools use tokenized service access, not a monthly subscription: when token_id is omitted the server returns payment_required with a Solana Pay invoice, and after payment you retry with the same token while the server uses Manus token/resolve to recover pending access."New value: +"Optional Chart access token (64-hex, same as X-Aipp-Chart / the token on /profile). After the daily free MCP quota, paid tools require the Chart $29/mo Stripe subscription. Legacy Manus token_id still works only when MCP_BILLING=manus."
  3. Added

TDQS

B3.3/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds the behavioral caveat that output is research bullets, not a trade signal, and implies a summary-style response. It does not contradict annotations.

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?

One dense sentence, front-loaded with the core purpose ('Salience card') and followed by a compact list of the card's contents. Every phrase earns its place, though the jargon list is heavy.

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

Completeness2/5

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

With no output schema, the description should explain the return shape and interpretation, but it only says 'Research bullets, not a trade' and lists metric names without defining them (e.g., 'D tightness', 'closest-twin vs median'). It also does not explain how parameters like f, q, or includeAnalogueCandles shape the card. For a 9-parameter tool with no output schema, this is a meaningful gap.

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 description coverage is 100%, so the schema already documents all nine parameters, including enums, defaults, and token/billing caveats. The description adds no parameter-specific meaning, but it does not need to; baseline 3 applies.

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?

The description identifies the tool as a 'Salience card for the current window' and enumerates the analyses it surfaces (neighbour band vs all-history width, ledger coverage vs 80%, closest-twin vs median, etc.), so an agent can tell it is an anomaly/research report rather than a trade execution tool. It lacks an explicit verb like 'returns' or 'computes,' and the jargon is dense, but the resource and scope are clear enough.

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

Usage Guidelines3/5

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

It gives a clear context cue: 'Research bullets, not a trade' tells the agent this is for research rather than actionable trading. However, it never states when to prefer this tool over siblings such as get_candle_evidence_board or explain_candle_match, nor does it list exclusions.

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