Skip to main content
Glama

Tape — Hyperliquid Analytics

Hyperliquid Markets Radar

tape_markets_radar
Read-onlyIdempotent

Rank live Hyperliquid perpetual markets by funding rate, funding APR, open interest, 24h volume or 24h change. Covers core Hyperliquid perps and a reviewed set of HIP-3 markets. New issues and pre-IPO markets are excluded. Default: the 25 markets with the most extreme funding APR, concise fields. Ask for limit, sort, coins, or DETAILED only when you need them. The full set is about 13k tokens. Result carries provenance (upstream endpoint, request, fetch time). For educational purposes only. Not trading advice. Not investment advice. Independent. Not affiliated with Hyperliquid Labs or the Hyperliquid Foundation.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "dir": "mag",
      "sort": "fundingAprPct",
      "coins": [
        "BTC",
        "ETH"
      ],
      "limit": 25,
      "response_format": "CONCISE"
    },
    "name": "tape_markets_radar"
  }
}

Input Schema

NameRequiredDescriptionDefault
dirNoDirection; `asc` on fundingAprPct surfaces the most negative funding first.
sortNoRanking key. Funding, premium and change sort by magnitude by default.
coinsNoRestrict to symbols, e.g. ["BTC","ETH"]. No -PERP suffix.
limitNoRows to return (default 25).
response_formatNoCONCISE (default): coin, mark, fundingAprPct, oi, vol. DETAILED: every field.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
      +  {
      +    "coins": [
      +      "BTC",
      +      "ETH"
      +    ],
      +    "dir": "mag",
      +    "limit": 25,
      +    "response_format": "CONCISE",
      +    "sort": "fundingAprPct"
      +  }
      +]
  2. First observed

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is settled. The description still adds genuinely new behavior: market coverage boundaries (HIP-3 reviewed set, new issues and pre-IPO excluded), the default ranking behavior, a ~13k token payload size for the full set, and a `provenance` field on results. It does not cover pagination mechanics or freshness/caching of the snapshot, so a solid but not exceptional 3.

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?

Purpose, coverage exclusions, default behavior, and cost warning all arrive before any padding, so the operational content is front-loaded. The trailing legal disclaimer ('For educational purposes only... Not affiliated with Hyperliquid Labs...') is four sentences that add no invocation value and dilute the signal. Tight and dense overall, with a noticeable tail of non-functional text.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description takes on return-value disclosure and does so by naming the concise field set and the `provenance` block. For a five-parameter, all-optional ranking tool with full schema coverage, the only real gap is not telling the agent how the ranking behaves for ties or whether results are a point-in-time snapshot. Nothing that would cause a mis-call 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?

Schema coverage is 100% with enums documented, so the baseline is 3. The description earns above baseline by explaining the consequence of not passing parameters (default rank by most extreme funding APR, concise fields) and by framing `limit`, `sort`, `coins`, and `response_format` as opt-in knobs whose cost is token volume. It stops short of explaining enum semantics like 'mag', which are left entirely to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: rank live Hyperliquid perpetual markets by funding rate, APR, open interest, volume, or 24h change. Scope is further sharpened with 'Covers core Hyperliquid perps and a reviewed set of HIP-3 markets' plus explicit exclusions for new issues and pre-IPO markets. It never names a sibling (tape_market_pulse, tape_market_signals, tape_analytics), so boundary-setting against the catalog is left to inference.

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?

Gives concrete default guidance: 'Default: the 25 markets with the most extreme funding APR, concise fields' and 'Ask for limit, sort, coins, or DETAILED only when you need them.' It also quantifies the cost of widening the call ('The full set is about 13k tokens'), which is directly actionable. No explicit when-not-to-use or named alternative tool, which keeps it from a 5.

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.

Resources