Skip to main content
Glama

Opportunity Scan

research_opportunities
Read-only

Cross-sectional opportunity scan across every major and medium-cap coin at once — the screener the per-coin tools cannot be looped into safely. Two whole-universe feeds (the merged market snapshot + venue perp contexts) build a liquidity-filtered universe and rank it, then candles are fetched for a bounded shortlist only; ZERO per-symbol calls are made to the rate-limited derivatives provider, which is what lets this cover a universe without silently degrading. Up to six signals per candidate: crowding (annualized funding vs the venue-standard anchor AND its percentile across the screened universe right now — a cross-sectional read, explicitly NOT the own-history percentile research_positioning reports), stress (24h liquidations as a share of open interest — whether forced sellers already cleared), leverage (open interest as a share of market cap — the gap-through-your-stop condition), compression (4h Bollinger bandwidth ranked against the coin's own trailing window — the per-coin form of the reading research_regime computes for BTC alone; says energy is loading, never direction), trend (ADX with the +DI/-DI separation on 4h, confirmed against 1d — the vote is withheld unless the slow timeframe agrees), and location (distance from the 4h EMA20 in ATR units — an extended coin scores DOWN, because a chase is not a setup). Each signal reports its state, the numbers, and a +1/0/-1 setup-quality vote; the setup name and score come from a disclosed rule shipped with every scan. Candidates carry ATR-and-structure geometry — a resting-limit entry at the EMA20 (never at market), a stop a full 2 ATR beyond it, and a target shaded inside the first structural level — priced so it feeds risk_position_size directly. 'tier' filters major/medium/all; 'limit' caps the ranked list; 'symbols' narrows the universe to specific coins, and every symbol named there is accounted for individually in the response — selected, excluded by your own tier filter, below the liquidity floors (never screened, so no band was ever applied to it), below the tier floor, or not quoted at all — because mere absence from the ranked list conflates four different answers. Reports a board, not a forecast: the bands are disclosed constants chosen for plausibility with no backtest behind them, and 'NO CANDIDATES' is a real and frequent answer. Use it to pick what to look at, then research_positioning and ta_technicals on the two or three that stand out.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tierNoSize tier to screen: 'major' (market cap >= $10B), 'medium' ($300M-$10B), or 'all' (default).
limitNoRanked candidates to return. Default 10, max 25.
symbolsNoOptional: narrow the universe to these coin symbols, e.g. ["SOL","AVAX"]. Omit to screen everything that clears the tier and liquidity floors.
intervalsNoThe timeframe pair to analyse, FINEST FIRST: [fast] or [fast, slow]. Default ["4h","1d"]. This is the most consequential argument: entry, stop, target, ATR and every AT STRUCTURE verdict are measured on the fast timeframe, so changing it produces a DIFFERENT trade rather than a refinement of the same one — on one live BTC read the 1h pair put the entry 0.2% above spot while the 1d pair put it 10.7% below, with stops of 0.77% and 3.31%. Lookbacks are counted in candles, so the swing windows scale too (30 candles is 5 days at 4h, 7 hours at 15m). The second interval only CONFIRMS the first and must be slower; pass one interval to skip confirmation, which halves the candle cost and makes the trend vote abstain.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
ruleNoThe exact rule that produced setup and score
caveatsNoWhat the scan cannot see, stated rather than implied
coverageNoWhat the scan actually looked at — read this before treating an empty candidate list as a quiet market
candidatesNo
requestedSymbolsNoOne entry per symbol named in the 'symbols' argument, so a symbol missing from 'candidates' can be explained. Empty when no symbols were named. A status other than 'selected' means no band was applied to that coin, so its absence says nothing about its setup.

TDQS

A4.8/5.0
Behavior5/5

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

Goes far beyond the sole readOnlyHint annotation, disclosing rate-limit avoidance ('ZERO per-symbol calls'), output interpretation ('says energy is loading, never direction'), and the un-backtested nature ('no backtest behind them'). It also tells the agent that 'NO CANDIDATES' is a real outcome, reducing the risk of misinterpreting empty results.

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 long but earns its length: the purpose is front-loaded, and the six signals are each covered with interpretive context rather than restating schema. It could be more scannable with bullets or paragraph breaks, but the density is justified for a tool with this many distinct outputs.

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?

Complete for an agent: it explains the screening approach, the liquidity-filtered universe, the per-signal meaning, the trade geometry, and the follow-up workflow into research_positioning and ta_technicals. With an output schema present, the description need not detail return fields; it still covers behavioral context and parameter effects thoroughly.

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?

Schema coverage is 100% and the schema descriptions are already thorough, so the baseline is 3. The description adds genuine extra semantics for 'symbols' ('every symbol named there is accounted for individually in the response — selected, excluded... or not quoted at all') and reinforces the 'intervals' behavior ('changing it produces a DIFFERENT trade rather than a refinement'), warranting a 4.

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 and resource: 'Cross-sectional opportunity scan across every major and medium-cap coin at once.' It also differentiates from sibling per-coin tools by explaining what it is not ('the screener the per-coin tools cannot be looped into safely') and explicitly references three siblings (research_positioning, research_regime, risk_position_size).

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?

Gives explicit when-to-use guidance: 'Use it to pick what to look at, then research_positioning and ta_technicals on the two or three that stand out.' It also contrasts with alternatives ('explicitly NOT the own-history percentile research_positioning reports'; 'the per-coin form of the reading research_regime computes for BTC alone'), so an agent knows exactly when to pick this tool over siblings.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0
Disambiguation4/5

Tools are grouped by clear prefixes and mostly target distinct resources; market_quotes vs research_token_view, market_top_movers vs market_trending, and funding_current vs market_quotes have some field or purpose overlap, but descriptions draw enough scope boundaries for an agent to choose correctly in most cases. No two tools are truly interchangeable.

Naming Consistency5/5

All 30 tool names use lowercase snake_case with a consistent domain-prefix convention such as market_, flow_, research_, sentiment_, and catalysts_, making the surface predictable. Even helpers like utc_time and risk_position_size fit the same noun-oriented pattern without style mixing.

Tool Count2/5

At 30 tools this set crosses the 'too many' threshold, and several tools reproduce data already available through broader ones such as research_token_view and market_quotes. The breadth is defensible for a crypto-research platform, but the surface feels heavy and could be consolidated.

Completeness5/5

The tool set covers the read-only crypto research workflow thoroughly: market data, candles, derivatives, funding, OI, order book, whale flows, ETF flows, on-chain metrics, news, sentiment, prediction odds, technicals, regime/positioning scans, and position sizing. It also includes health and UTC helpers that close practical workflow gaps, with no obvious dead ends.

Resources