Skip to main content
Glama
Coinversaa

Coinversaa Pulse

Official

pulse_recent_trades

Retrieve the largest trades on Hyperliquid within a specified time window, sorted by absolute profit and loss to identify market movers. Filter by coin or limit results for targeted insights.

Instructions

Get the biggest trades on Hyperliquid in the last N minutes/hours. Returns trades sorted by absolute PnL — the largest movers. Use this to see what's happening right now on the exchange.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
useToonFormatNoReturn data in compact toon format (default: true). Set to false for standard JSON.
sinceNoTime window: e.g. '10m' (minutes), '1h' (hours), '1d' (days)10m
limitNoNumber of trades to return
coinNoFilter by coin symbol (e.g. BTC, ETH, SOL). For builder dex: prefix:COIN (e.g. xyz:SILVER)

Implementation Reference

  • src/index.ts:485-501 (registration)
    Registration of the 'pulse_recent_trades' tool via server.registerTool with its input schema (useToonFormat, since, limit, coin) and handler. The tool is conditionally registered based on API key availability via shouldRegister().
    if (shouldRegister("pulse_recent_trades")) server.registerTool(
      "pulse_recent_trades",
      {
        description: "Get the biggest trades on Hyperliquid in the last N minutes/hours. Returns trades sorted by absolute PnL — the largest movers. Use this to see what's happening right now on the exchange.",
        inputSchema: {
          useToonFormat: useToonFormatSchema,
          since: sinceSchema.default("10m"),
          limit: z.number().min(1).max(100).default(20).describe("Number of trades to return"),
          coin: z.string().optional().describe("Filter by coin symbol (e.g. BTC, ETH, SOL). For builder dex: prefix:COIN (e.g. xyz:SILVER)"),
        },
      },
      async ({ useToonFormat, since, limit, coin }) => {
        const params: Record<string, string> = { since, limit: String(limit) };
        if (coin) params.coin = normalizeCoin(coin);
        return toolResult(await callAPI(useToonFormat, "/pulse/trades/recent", params));
      }
    );
  • Handler function for pulse_recent_trades: builds params object with 'since' and 'limit', optionally normalizes the 'coin' parameter, then calls the API at endpoint '/pulse/trades/recent' via the callAPI helper.
      async ({ useToonFormat, since, limit, coin }) => {
        const params: Record<string, string> = { since, limit: String(limit) };
        if (coin) params.coin = normalizeCoin(coin);
        return toolResult(await callAPI(useToonFormat, "/pulse/trades/recent", params));
      }
    );
  • Input schema definition for pulse_recent_trades: useToonFormat (boolean, default true), since (regex-validated time window, default '10m'), limit (1-100, default 20), and optional coin filter.
    {
      description: "Get the biggest trades on Hyperliquid in the last N minutes/hours. Returns trades sorted by absolute PnL — the largest movers. Use this to see what's happening right now on the exchange.",
      inputSchema: {
        useToonFormat: useToonFormatSchema,
        since: sinceSchema.default("10m"),
        limit: z.number().min(1).max(100).default(20).describe("Number of trades to return"),
        coin: z.string().optional().describe("Filter by coin symbol (e.g. BTC, ETH, SOL). For builder dex: prefix:COIN (e.g. xyz:SILVER)"),
      },
    },
  • The normalizeCoin helper function used by the handler to normalize coin/symbol strings (uppercasing the ticker while preserving builder dex prefix case).
    function normalizeCoin(raw: string): string {
      const idx = raw.indexOf(':');
      if (idx !== -1) {
        // Builder dex format — keep prefix lowercase, uppercase the coin
        return raw.slice(0, idx).toLowerCase() + ':' + raw.slice(idx + 1).toUpperCase();
      }
      return raw.toUpperCase();
    }
  • The callAPI helper function used by the handler to make HTTP requests to the backend API with timeout, retries, and error handling.
    async function callAPI(useToon: boolean, path: string, params?: Record<string, string>): Promise<any> {
      const url = new URL(`${BASE}${path}`);
      if (params) {
        Object.entries(params).forEach(([key, value]) => {
          if (value !== undefined && value !== "") {
            url.searchParams.set(key, value);
          }
        });
      }
    
      let lastError: Error | null = null;
    
      for (let attempt = 0; attempt <= MAX_RETRIES; attempt++) {
        try {
          const controller = new AbortController();
          const timeout = setTimeout(() => controller.abort(), REQUEST_TIMEOUT_MS);
    
          const headers: Record<string, string> = {};
          if (API_KEY) headers["X-API-Key"] = API_KEY;
    
          const response = await fetch(url.toString(), {
            headers,
            signal: controller.signal,
          });
    
          clearTimeout(timeout);
    
          if (response.status === 429) {
            // Rate limited — retry after delay
            if (attempt < MAX_RETRIES) {
              await new Promise((r) => setTimeout(r, RETRY_DELAY_MS * (attempt + 1)));
              continue;
            }
            throw new Error("Rate limit exceeded. Please wait a moment and try again.");
          }
    
          if (response.status === 404) {
            throw new Error("Not found. The requested resource does not exist — check the address or symbol.");
          }
    
          if (response.status === 401) {
            throw new Error("Invalid API key. Check your COINVERSAA_API_KEY environment variable.");
          }
    
          if (!response.ok) {
            const body = await response.json().catch(() => null);
            const msg = body?.error || response.statusText;
            throw new Error(`Request failed (${response.status}): ${msg}`);
          }
    
          const data = await response.json();
          return useToon ? toonEncode(data) : data;
        } catch (err: any) {
          if (err.name === "AbortError") {
            lastError = new Error("Request timed out after 30 seconds. The server may be under heavy load — try again.");
          } else if (err.cause?.code === "ECONNREFUSED" || err.cause?.code === "ENOTFOUND") {
            lastError = new Error("Cannot connect to the Coinversa API. Check your COINVERSAA_API_URL setting and network connection.");
          } else {
            lastError = err;
          }
    
          // Retry on transient network errors
          if (attempt < MAX_RETRIES && (err.name === "AbortError" || err.cause?.code === "ECONNRESET")) {
            await new Promise((r) => setTimeout(r, RETRY_DELAY_MS * (attempt + 1)));
            continue;
          }
    
          throw lastError;
        }
      }
    
      throw lastError || new Error("Request failed after retries");
    }
Behavior4/5

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

No annotations are provided, so the description must disclose behavior. It explains the sorting by absolute PnL and the time window, which covers key behavioral aspects for a read-only tool. However, it does not mention any limitations or potential side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise at two sentences, with no filler. It front-loads the purpose and includes a clear usage note.

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?

For a simple list retrieval tool without output schema, the description provides adequate context about what the tool returns and its sorting. It could mention that it returns top trades by PnL, but it's complete enough for an agent to use.

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%, so the baseline is 3. The description does not add additional parameter context beyond what is already in the input 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?

The description clearly states the tool retrieves the biggest trades on Hyperliquid sorted by absolute PnL, with a time window. It distinguishes itself from siblings by emphasizing recency and PnL sorting, though not explicitly differentiating from pulse_biggest_trades.

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 includes a usage hint ('Use this to see what's happening right now') but does not specify when to avoid using it or mention alternatives like pulse_biggest_trades.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Coinversaa/mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server