Skip to main content
Glama
Coinversaa

Coinversaa Pulse

Official

pulse_cohort_bias_history

Access historical hourly bias snapshots for trader cohorts. See net long/short notional and account counts per tier to track how whales and smart money shifted positions. Supports per-coin or global aggregate up to 30 days.

Instructions

Get historical hourly bias snapshots for all trader cohorts. Returns net long/short notional and account counts per tier. Use this to see how different groups (whales, smart money) have shifted their positioning over time. Supports per-coin or global aggregate. Max range is 30 days.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
useToonFormatNoReturn data in compact toon format (default: true). Set to false for standard JSON.
coinNoFilter by coin symbol (e.g. BTC, ETH, SOL). For builder dex: prefix:COIN (e.g. xyz:SILVER). Omit for global exchange aggregate.
sinceNoTime window for history (max 30d). e.g. '24h', '7d', '30d'
startTimeNoExplicit start time (ISO string or timestamp). Overrides 'since'.
endTimeNoExplicit end time (ISO string or timestamp). Defaults to now.

Implementation Reference

  • src/index.ts:956-977 (registration)
    Tool registration for pulse_cohort_bias_history using server.tool (rather than server.registerTool). The tool is registered with input schema (useToonFormat, coin, since, startTime, endTime) and delegates to callAPI('/pulse/cohort-bias/history', ...).
    // ══════════════════════════════════════════════════════════
    // TOOL 29: Cohort Bias History
    // ══════════════════════════════════════════════════════════
    if (shouldRegister("pulse_cohort_bias_history")) server.tool(
      "pulse_cohort_bias_history",
      "Get historical hourly bias snapshots for all trader cohorts. Returns net long/short notional and account counts per tier. Use this to see how different groups (whales, smart money) have shifted their positioning over time. Supports per-coin or global aggregate. Max range is 30 days.",
      {
        useToonFormat: useToonFormatSchema,
        coin: z.string().optional().describe("Filter by coin symbol (e.g. BTC, ETH, SOL). For builder dex: prefix:COIN (e.g. xyz:SILVER). Omit for global exchange aggregate."),
        since: sinceSchema.optional().describe("Time window for history (max 30d). e.g. '24h', '7d', '30d'"),
        startTime: z.string().optional().describe("Explicit start time (ISO string or timestamp). Overrides 'since'."),
        endTime: z.string().optional().describe("Explicit end time (ISO string or timestamp). Defaults to now."),
      },
      async ({ useToonFormat, coin, since, startTime, endTime }) => {
        const params: Record<string, string> = {};
        if (since) params.since = since;
        if (startTime) params.startTime = startTime;
        if (endTime) params.endTime = endTime;
        if (coin) params.coin = normalizeCoin(coin);
        return toolResult(await callAPI(useToonFormat, "/pulse/cohort-bias/history", params));
      }
    );
  • Handler function for pulse_cohort_bias_history. Accepts optional useToonFormat, coin, since, startTime, endTime params, builds a params object, and calls the API at /pulse/cohort-bias/history.
      async ({ useToonFormat, coin, since, startTime, endTime }) => {
        const params: Record<string, string> = {};
        if (since) params.since = since;
        if (startTime) params.startTime = startTime;
        if (endTime) params.endTime = endTime;
        if (coin) params.coin = normalizeCoin(coin);
        return toolResult(await callAPI(useToonFormat, "/pulse/cohort-bias/history", params));
      }
    );
  • Input schema for pulse_cohort_bias_history: useToonFormat (boolean, default true), coin (optional string), since (optional time window string), startTime (optional ISO/timestamp string), endTime (optional ISO/timestamp string).
    {
      useToonFormat: useToonFormatSchema,
      coin: z.string().optional().describe("Filter by coin symbol (e.g. BTC, ETH, SOL). For builder dex: prefix:COIN (e.g. xyz:SILVER). Omit for global exchange aggregate."),
      since: sinceSchema.optional().describe("Time window for history (max 30d). e.g. '24h', '7d', '30d'"),
      startTime: z.string().optional().describe("Explicit start time (ISO string or timestamp). Overrides 'since'."),
      endTime: z.string().optional().describe("Explicit end time (ISO string or timestamp). Defaults to now."),
    },
  • build/index.js:707-727 (registration)
    Same tool registration in the built/compiled version (build/index.js). Uses server.tool() and the same logic.
    // TOOL 29: Cohort Bias History
    // ══════════════════════════════════════════════════════════
    if (shouldRegister("pulse_cohort_bias_history"))
        server.tool("pulse_cohort_bias_history", "Get historical hourly bias snapshots for all trader cohorts. Returns net long/short notional and account counts per tier. Use this to see how different groups (whales, smart money) have shifted their positioning over time. Supports per-coin or global aggregate. Max range is 30 days.", {
            useToonFormat: useToonFormatSchema,
            coin: z.string().optional().describe("Filter by coin symbol (e.g. BTC, ETH, SOL). For builder dex: prefix:COIN (e.g. xyz:SILVER). Omit for global exchange aggregate."),
            since: sinceSchema.optional().describe("Time window for history (max 30d). e.g. '24h', '7d', '30d'"),
            startTime: z.string().optional().describe("Explicit start time (ISO string or timestamp). Overrides 'since'."),
            endTime: z.string().optional().describe("Explicit end time (ISO string or timestamp). Defaults to now."),
        }, async ({ useToonFormat, coin, since, startTime, endTime }) => {
            const params = {};
            if (since)
                params.since = since;
            if (startTime)
                params.startTime = startTime;
            if (endTime)
                params.endTime = endTime;
            if (coin)
                params.coin = normalizeCoin(coin);
            return toolResult(await callAPI(useToonFormat, "/pulse/cohort-bias/history", params));
        });
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It discloses the tool returns historical snapshots with notional and counts, but lacks details on rate limits, authentication, or response behavior. The read-only nature is implied but not explicitly stated.

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 three sentences, each serving a clear purpose: stating the function, the output, and usage guidance. No redundant information, front-loaded with the core action.

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?

The description adequately explains the purpose, input scope (per-coin/global, 30-day max), and output content (notional and counts) for a tool without an output schema. It lacks details on response structure beyond mentioning 'toon format,' but is sufficient for most usage scenarios.

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 baseline is 3. The description adds context like 'per-coin or global aggregate' and 'max range 30 days,' which aligns with parameters but does not introduce new semantics beyond the schema descriptions.

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 historical hourly bias snapshots for trader cohorts, specifying the returned data (net long/short notional and account counts per tier). It distinguishes from siblings like live_cohort_bias (current) by emphasizing 'historical,' but does not explicitly name alternatives.

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 says 'Use this to see how different groups have shifted their positioning over time,' providing a clear use case. However, it does not specify when not to use it or compare with sibling tools like pulse_cohort_history or live_cohort_bias.

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