Abnormal open-interest jumps across ~600 USDT perps vs a 30min+ baseline — where new leverage is piling in, with funding and price context. Squeeze/flush precursor screener. Costs $0.02 USDC per call (x402, Solana mainnet).
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | top N, 1-25, default 10 |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the safety/cost/burden disclosure. It explicitly states the $0.02 USDC cost per call and the x402/Solana mainnet execution context, and describes the baseline logic (30min+ baseline) and output context. It stops short of disclosing exact thresholds or response shape, but this is sufficient for a simple read-only scan.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three short sentences front-load the core behavior first, then the use-case label, then cost. Every clause adds distinct value with zero filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has one optional parameter, no output schema, and no annotations, so the description must carry the burden. It covers the universe, the detection logic, the funding/price context, and the cost. It does not explicitly describe the return format or ranking order, but for a screener of this simplicity the description is nearly complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already describes `limit` as 'top N, 1-25, default 10' with 100% coverage, so the baseline is 3. The description does not add anything specific to the parameter beyond naming the scan universe, so it neither helps nor hurts.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description identifies a specific screening behavior ('Abnormal open-interest jumps across ~600 USDT perps vs a 30min+ baseline'), names the output context (funding and price), and labels the tool as a 'Squeeze/flush precursor screener'. This clearly distinguishes it from siblings like get_open_interest or get_squeeze_score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It states the intended use case ('Squeeze/flush precursor screener') and the scan universe, providing clear context for when to call it. It does not explicitly name alternative tools or exclusion conditions, but the context is strong enough for an agent to route correctly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Many tools are tightly scoped and cross-referenced, but the set contains overlapping families: liquidation tools (alert/scan/history/stats/leaders/recent/heatmap) and redundant snapshots like get_market_snapshot vs get_trade_context, get_last_liquidation vs get_recent_liquidations, and get_cascade_forecast_free vs get_cascade_forecast. Agents will need to read descriptions carefully to avoid misselection.
All tool names follow a consistent get_<domain>_<detail> snake_case pattern, which makes the API predictable. The only real deviations are the bare 'pricing' tool and the 'free' suffix on taster variants.
At 52 tools, this far exceeds the 3-15 well-scoped range and crosses the 50-tool extreme threshold. The count is inflated by numerous paid/free taster pairs and many overlapping liquidation variants.
The surface covers prices, funding, open interest, orderbooks, liquidations, wallet/token data, Solana network health, DeFi TVL, and stablecoin flows—broad coverage for a crypto data feed. Gaps like historical OHLC/price candles, a machine-readable symbol list, and pagination endpoints are workable around but would round it out.