Skip to main content
Glama

Trader Alpha Signals

trader_signals

Scan Verilex datasets for alpha signals: 8-K filings, short interest spikes, new patents, trademarks, litigation, and delinquent filers. Set lookback from 1 to 90 days.

Instructions

Get recent alpha signals for traders and hedge funds. Signals include new 8-K filings, short interest spikes, new patent grants, new trademark filings, new litigation, and delinquent filers. Scans activity across all Verilex datasets over a configurable lookback period.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
daysNoLookback period in days (default 7, max 90)
signal_typesNoFilter to specific signal types (default: all)
limitNoMaximum signals to return (default 100, max 500)

Implementation Reference

  • The 'trader_signals' tool is registered via server.registerTool() with the name 'trader_signals'. The registration includes title 'Trader Alpha Signals', description, inputSchema (days, signal_types, limit), and the async handler function.
    server.registerTool(
      "trader_signals",
      {
        title: "Trader Alpha Signals",
        description:
          "Get recent alpha signals for traders and hedge funds. Signals include new 8-K filings, " +
          "short interest spikes, new patent grants, new trademark filings, new litigation, " +
          "and delinquent filers. Scans activity across all Verilex datasets over a configurable lookback period.",
        inputSchema: {
          days: z
            .number()
            .int()
            .min(1)
            .max(90)
            .optional()
            .describe("Lookback period in days (default 7, max 90)"),
          signal_types: z
            .array(z.enum([
              "new_8k",
              "short_interest_spike",
              "new_patent",
              "new_trademark",
              "new_litigation",
              "delinquent_filer",
            ]))
            .optional()
            .describe("Filter to specific signal types (default: all)"),
          limit: z
            .number()
            .int()
            .min(1)
            .max(500)
            .optional()
            .describe("Maximum signals to return (default 100, max 500)"),
        },
      },
      async ({ days, signal_types, limit }) => {
        const res = await apiGet<{
          dataset: string;
          lookback_days: number;
          count: number;
          signals: Record<string, unknown>[];
        }>("/api/v1/companies/signals", {
          days: days ?? 7,
          signal_types: signal_types ? signal_types.join(",") : undefined,
          limit: limit ?? 100,
        });
    
        if (!res.ok) {
          return {
            content: [
              {
                type: "text" as const,
                text: `API error (${res.status}): ${JSON.stringify(res.data)}`,
              },
            ],
            isError: true,
          };
        }
    
        const { lookback_days, count, signals } = res.data;
        const summary = `Found ${count} signal(s) in the last ${lookback_days} days.`;
        const json = JSON.stringify(signals, null, 2);
    
        return {
          content: [{ type: "text" as const, text: `${summary}\n\n${json}` }],
        };
      },
    );
  • The handler function for 'trader_signals' accepts { days, signal_types, limit }, calls apiGet to /api/v1/companies/signals with optional query parameters, and returns the formatted response with signal count and data.
    async ({ days, signal_types, limit }) => {
      const res = await apiGet<{
        dataset: string;
        lookback_days: number;
        count: number;
        signals: Record<string, unknown>[];
      }>("/api/v1/companies/signals", {
        days: days ?? 7,
        signal_types: signal_types ? signal_types.join(",") : undefined,
        limit: limit ?? 100,
      });
    
      if (!res.ok) {
        return {
          content: [
            {
              type: "text" as const,
              text: `API error (${res.status}): ${JSON.stringify(res.data)}`,
            },
          ],
          isError: true,
        };
      }
    
      const { lookback_days, count, signals } = res.data;
      const summary = `Found ${count} signal(s) in the last ${lookback_days} days.`;
      const json = JSON.stringify(signals, null, 2);
    
      return {
        content: [{ type: "text" as const, text: `${summary}\n\n${json}` }],
      };
    },
  • Input schema for 'trader_signals': days (int 1-90, default 7), signal_types (array of enum values: new_8k, short_interest_spike, new_patent, new_trademark, new_litigation, delinquent_filer), limit (int 1-500, default 100).
    inputSchema: {
      days: z
        .number()
        .int()
        .min(1)
        .max(90)
        .optional()
        .describe("Lookback period in days (default 7, max 90)"),
      signal_types: z
        .array(z.enum([
          "new_8k",
          "short_interest_spike",
          "new_patent",
          "new_trademark",
          "new_litigation",
          "delinquent_filer",
        ]))
        .optional()
        .describe("Filter to specific signal types (default: all)"),
      limit: z
        .number()
        .int()
        .min(1)
        .max(500)
        .optional()
        .describe("Maximum signals to return (default 100, max 500)"),
    },
Behavior3/5

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

No annotations are provided, so the description must carry the full burden. It explains that it scans all Verilex datasets with a configurable lookback, but omits details like auth needs, rate limits, or result handling.

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?

Three sentences with clear front-loading: purpose, signal list, and scanning scope. No redundant words.

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 tool with 3 fully described parameters and no output schema, the description adequately covers purpose and scope. Minor gap: output format not hinted.

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 description coverage is 100%, so the description adds little beyond repeating parameter names and listing signal types already in the schema enum.

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?

The description uses a specific verb ('Get') and resource ('alpha signals') and lists six concrete signal types, clearly distinguishing it from siblings like pm_signals by mentioning Verilex datasets.

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 implies usage for retrieving alpha signals but provides no explicit guidance on when to use this tool versus alternatives like pm_signals, nor any when-not-to-use conditions.

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/carrierone/verilexdata-mcp'

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