Skip to main content
Glama
Sign In

Annalist

by io.github.ryanroskowski
OverviewDiscussionsAdmin

Crowd state for one Hyperliquid perp

crowd_perp
Read-only

Use before acting on a Hyperliquid perpetual to see whether it is crowded or in a hype state and what historically followed. Returns 7-day move, funding (hourly, APR, percentile vs its own 90 days and vs all perps), open interest and its 24h/7d change, premium, Wikipedia attention, active crowd states, and each state's base rates (sample size, median and spread of 7/30/90-day returns). Signed. Not investment advice. Price: $0.01 USDC per call via x402 (Base or Solana).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "coin": "<coin>"
    },
    "name": "crowd_perp"
  }
}

Input Schema

NameRequiredDescriptionDefault
coinYesHyperliquid perp symbol, for example BTC, ETH, SOL, HYPE, kPEPE (case-sensitive)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

Adds meaningful context beyond the readOnly/openWorld annotations: it is signed, is not investment advice, and costs $0.01 USDC per call via x402 on Base or Solana — a critical non-obvious billing/authorization trait. It does not disclose rate limits, caching, or latency, which keeps it short of a 5.

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 usage-condition and payment/safety items are correctly front-loaded and back-loaded, but the return-value enumeration ('7-day move, funding... base rates') is a long, dense list that could be compressed. Not egregious, but not tight.

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?

No output schema exists, so the description usefully enumerates the returned fields (funding, open interest, premium, attention, crowd states, base rates). The main gap is that it does not describe the response structure/format for those fields, but for a single-coin analytical read the coverage is good.

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?

Schema coverage is 100% and the single coin parameter already documents case-sensitive Hyperliquid symbols with examples, so the description needn't add syntax. Baseline 3 applies since the schema carries the parameter semantics.

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 (see) and resource (whether a Hyperliquid perpetual is crowded or in a hype state) plus the forward-looking payoff (what historically followed). An agent can distinguish this from siblings like crowd_market, crowd_history, or perp_full without opening those schemas.

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?

Explicit temporal guidance: 'Use before acting on a Hyperliquid perpetual.' It does not, however, name or exclude alternative siblings (crowd_market, crowd_history, perp_full) or state when not to use it.

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

All Annalist toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources