Skip to main content
Glama

Ichimoku Signal

by io.github.Fizzl13
OverviewDiscussionsAdmin

Trade setups: every top-200 coin, ranked ($0.50 via x402)

trade_setups
Read-only

Paid ($0.50 USDC via x402 on Solana or Base): which crypto coins have a trade setup right now. For 148 top-200 coins: the six-indicator confluence signal (Ichimoku, RSI, MACD, EMA 50/200, Bollinger, OBV) and a trade plan in that direction (entry, stop, two take profit targets, risk/reward), ranked by signal strength x risk/reward, lower for high volatility, for support/resistance right after the entry and for thinly traded coins. Filters: direction (long/short/both), min_rr, top, liquid_top (only the N most traded coins). The screener across all coins; for one pair you already chose use confluence_signal and price_levels. Same as GET /setups. Levels from price history, not trade advice. A screener, not a strategy: in our backtest these setups did no better than random entries after fees.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
topNoHow many setups to return (default 10)
min_rrNoMinimum risk/reward to target 1 (default 1.5)
intervalNoCandle interval, default 4h
directionNoOnly long or only short setups (default both)
liquid_topNoOnly the N most traded coins, e.g. 30 (default all)

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
setupsNoRanked setups with entry, stop and targets
acceptsNoOnly on an unpaid call: the x402 payment options
intervalNo
timestampNo
setups_foundNo
coins_scannedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": true,
+  "properties": {
+    "accepts": {
+      "anyOf": [
+        {
+          "items": {
+            "additionalProperties": {},
+            "type": "object"
+          },
+          "type": "array"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "Only on an unpaid call: the x402 payment options"
+    },
+    "coins_scanned": {
+      "type": [
+        "number",
+        "null"
+      ]
+    },
+    "interval": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "setups": {
+      "anyOf": [
+        {
+          "items": {
+            "additionalProperties": {},
+            "type": "object"
+          },
+          "type": "array"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "Ranked setups with entry, stop and targets"
+    },
+    "setups_found": {
+      "type": [
+        "number",
+        "null"
+      ]
+    },
+    "timestamp": {
+      "type": [
+        "string",
+        "null"
+      ]
+    }
+  },
+  "type": "object"
+}
  2. Changed1 schema field changed
    • addedInput schema / properties / liquid_top
      Added value: +{
+  "description": "Only the N most traded coins, e.g. 30 (default all)",
+  "maximum": 200,
+  "minimum": 1,
+  "type": "integer"
+}
  3. Added

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the readOnly/openWorld annotations by disclosing the x402 payment ($0.50 USDC on Solana or Base), the ranking formula (signal strength x risk/reward, penalized for volatility, nearby support/resistance, thin liquidity), and a candid backtest caveat that the setups did no better than random after fees. This is unusually rich behavioral context.

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?

Front-loads the paid access and core purpose, then packs filters, ranking logic, and caveats efficiently. The middle clause is dense and run-on, but nearly every sentence carries information; minor tightening possible.

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?

With an output schema present, return values need not be described. The description covers payment, scope, ranking rationale, alternatives, and a critical expectation-setting caveat, leaving no significant gap for an agent deciding whether to call it.

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 the schema already documents all five parameters. The description restates four of them (direction, min_rr, top, liquid_top) without adding format or syntax detail beyond what's in the schema, and omits interval entirely. Baseline 3 applies when the schema does the heavy lifting.

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?

States a specific verb+resource: it returns 'which crypto coins have a trade setup right now' across 148 top-200 coins, using a six-indicator confluence signal plus a trade plan. It explicitly distinguishes itself from siblings by naming confluence_signal and price_levels for the single-pair case.

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

Usage Guidelines5/5

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

Names the alternatives (confluence_signal, price_levels) and the condition that selects them ('for one pair you already chose'). Also enumerates the available filters (direction, min_rr, top, liquid_top) so the caller knows how to scope the result.

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

All Ichimoku Signal 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