f1ow

Token Deep Dive

research_token_view

Read-only

Aggregated single-coin dossier: market data (spot/perp price, funding, market-wide OI, long/short, liquidations — the same enriched line as market_quotes), global market context (dominance, Fear & Greed), multi-timeframe technicals computed in-house from candles (4h + 1d: RSI, EMA/SMA, MACD, ATR, Bollinger, ADX, trend — the same numbers as ta_technicals), on-chain TVL/fees (when the symbol is a tracked chain), news, a grounded narrative synthesis with citations, upcoming catalyst events, social sentiment, ETF flows, prediction-market odds, live provider coverage, and a per-section status list that distinguishes an empty section from a failed feed — for one symbol (e.g. 'ETH').

Input Schema

TableJSON Schema

Name	Required	Description	Default
`symbol`	Yes	Coin symbol, e.g. 'ETH' or 'BTC'

Output Schema

TableJSON Schema

Name	Required	Description
`news`	No
`market`	No	Same shape as one market_quotes item; omitted when no provider covers the symbol
`social`	No
`symbol`	Yes
`etfFlow`	No
`onChain`	No
`sections`	No	Per-section outcome, so an empty section can be told apart from a failed feed. Check this before reading an empty array as a real absence.
`catalysts`	No
`narrative`	No
`technicals`	No	In-house per-timeframe snapshots; same item shape as ta_technicals's timeframes. Empty when no timeframe could be analyzed.
`marketContext`	No	Same shape as market_overview
`providerCoverage`	No
`predictionMarkets`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedSep 19, 2026

addedOutput schema / properties / news / items / properties / coins

Added value: +{
+  "description": "Coin symbols the feed tagged on the item, e.g. [\"BTC\",\"ETH\"]",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedOutput schema / properties / news / items / properties / impact

Added value: +{
+  "description": "Measured price move after the headline broke; omitted when not measured",
+  "properties": {
+    "coin": {
+      "type": "string"
+    },
+    "down": {
+      "description": "Worst move reached in the window, percentage points",
+      "type": "number"
+    },
+    "pct": {
+      "description": "Net move over the window, percentage points, e.g. 1.9",
+      "type": "number"
+    },
+    "up": {
+      "description": "Best move reached in the window, percentage points",
+      "type": "number"
+    },
+    "windowMs": {
+      "description": "Measurement window in milliseconds, e.g. 3600000",
+      "type": "number"
+    }
+  },
+  "type": "object"
+}

addedOutput schema / properties / news / items / properties / kind

Added value: +{
+  "description": "Item type: article, tweet or exchange (announcement); empty when the feed doesn't say",
+  "type": "string"
+}

First observedAug 19, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already mark it read-only, and the description adds meaningful behavioral context: it is an aggregate assembled from multiple feeds, on-chain data is conditional on the symbol being tracked, and it includes a per-section status list that distinguishes empty sections from failed feeds. This goes beyond the annotation without contradicting it.

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 description is one dense front-loaded sentence that starts with the core purpose before listing sections. It is long, but almost every clause names a distinct output category or caveat, so the length is justified by the tool's breadth; breaking it into bullets would improve scannability.

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?

Given a simple input schema, a read-only annotation, and an output schema that covers return structure, the description covers the relevant behaviors and conditional cases (tracked chains, per-section failures, live provider coverage). An agent has enough information to call this tool and interpret its aggregated result.

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?

With 100% schema description coverage for the sole symbol parameter, the schema already documents the meaning and example. The description repeats the one-symbol scope and ETH example but does not add constraints like case-sensitivity, accepted symbol formats, or validation behavior, so it stays at baseline.

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 'Aggregated single-coin dossier' and enumerates the full set of data categories for one symbol, so an agent immediately knows what the tool returns. It also distinguishes itself from siblings by noting equivalent content to market_quotes and ta_technicals, making its aggregation role explicit.

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?

The description strongly implies this is the broad overview tool and points out where its data overlaps with market_quotes and ta_technicals, but it never explicitly says when to prefer this over a specialized sibling. There is no when-not guidance or alternative routing, so an agent must infer the usage boundary.

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

All f1ow 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?