whale-insights

leverage_picks_summary

Read-onlyIdempotent

Get Leverage Radar pick accuracy summary — historical win rate, avg return, and total pick counts across all recorded Best Trade Now picks — Aggregate accuracy statistics for all 'Best Trade Now' picks recorded by the Leverage Radar tool. Picks are saved automatically every 5 minutes when a high-confidence setup (score ≥ 60) is detected across 1h/4h/12h windows. Outcome is resolved after the close window elapses using live price data: win = +1.5% return for buy / −1.5% for sell. Records are permanent (never deleted) — this is a live data-provider proof-of-accuracy archive. Full pick list with entry/exit prices is Pro-only. 30-min cache.

Input Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Output Schema

TableJSON Schema

Name	Required	Description
`note`	No
`wins`	No	Picks classified as win.
`losses`	No	Picks classified as loss.
`windows`	No	Trading windows tracked: 1h (scalp), 4h (swing), 12h (position).
`neutrals`	No	Picks within ±1.5% (neutral).
`updatedAt`	No
`dataSource`	No
`totalPicks`	No	Total picks ever recorded (pending + resolved).
`winRatePct`	No	Win rate as a percentage (0–100). Null until first resolved picks exist.
`attribution`	No
`avgReturnPct`	No	Average return % across all resolved picks (positive = profitable on avg).
`pendingPicks`	No	Picks still awaiting resolution (close window not yet elapsed).
`resolvedPicks`	No	Picks with outcome resolved (close window elapsed).
`avgWinReturnPct`	No	Average return % for winning picks only.
`winThresholdPct`	No	Return threshold used to classify a pick as win/loss (currently 1.5%).

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 3, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "attribution": {
+      "$ref": "#/components/schemas/Attribution"
+    },
+    "avgReturnPct": {
+      "description": "Average return % across all resolved picks (positive = profitable on avg).",
+      "nullable": true,
+      "type": "number"
+    },
+    "avgWinReturnPct": {
+      "description": "Average return % for winning picks only.",
+      "nullable": true,
+      "type": "number"
+    },
+    "dataSource": {
+      "type": "string"
+    },
+    "losses": {
+      "description": "Picks classified as loss.",
+      "type": "integer"
+    },
+    "neutrals": {
+      "description": "Picks within ±1.5% (neutral).",
+      "type": "integer"
+    },
+    "note": {
+      "type": "string"
+    },
+    "pendingPicks": {
+      "description": "Picks still awaiting resolution (close window not yet elapsed).",
+      "type": "integer"
+    },
+    "resolvedPicks": {
+      "description": "Picks with outcome resolved (close window elapsed).",
+      "type": "integer"
+    },
+    "totalPicks": {
+      "description": "Total picks ever recorded (pending + resolved).",
+      "type": "integer"
+    },
+    "updatedAt": {
+      "format": "date-time",
+      "type": "string"
+    },
+    "winRatePct": {
+      "description": "Win rate as a percentage (0–100). Null until first resolved picks exist.",
+      "nullable": true,
+      "type": "number"
+    },
+    "winThresholdPct": {
+      "description": "Return threshold used to classify a pick as win/loss (currently 1.5%).",
+      "type": "number"
+    },
+    "windows": {
+      "description": "Trading windows tracked: 1h (scalp), 4h (swing), 12h (position).",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "wins": {
+      "description": "Picks classified as win.",
+      "type": "integer"
+    }
+  },
+  "type": "object"
+}

AddedJul 17, 2026

TDQS

A4.5/5.0

Behavior5/5

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

The annotations (readOnlyHint, idempotentHint, destructiveHint false) cover safety, and the description adds substantial behavioral detail: picks auto-save every 5 minutes, selection requires score ≥ 60 across 1h/4h/12h windows, win is defined as ±1.5%, records are permanent, full list is Pro-only, and data is cached for 30 minutes. This goes far beyond structured fields.

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?

The description is front-loaded and information-dense, but the first two sentences are largely redundant: 'Get Leverage Radar pick accuracy summary ... across all recorded Best Trade Now picks' is repeated by 'Aggregate accuracy statistics for all Best Trade Now picks recorded by the Leverage Radar tool.' The rest is valuable, but the repetition keeps it from being maximally tight.

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?

For a zero-parameter read-only tool with an output schema, the description covers data provenance, sampling cadence, win/loss criteria, persistence guarantees, access restrictions, and cache behavior. There is nothing an agent needs to call or interpret this tool that is missing.

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?

There are zero input parameters and schema coverage is 100%, so the baseline is 4. The description adds meaning by explaining exactly what data is aggregated (win rate, avg return, counts) and its selection criteria, helping the agent match the tool to user intent even without any params to document.

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 opens with 'Get Leverage Radar pick accuracy summary' — a specific verb and resource — and immediately enumerates the exact outputs: 'historical win rate, avg return, and total pick counts'. It clearly differentiates from siblings like leverage_history and leverage_radar by focusing on aggregated accuracy statistics rather than raw signals or history.

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?

The description gives very clear context: this is for aggregate accuracy stats on 'Best Trade Now' picks, resolved against live price data. However, it never explicitly names alternatives or states when not to use it, so the agent must infer routing from the sibling list rather than being told.

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

All whale-insights tools Inspect

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

Need Help?