Skip to main content
Glama

golden_alerts_history

Read-onlyIdempotent

Golden Alerts history (daily summaries) — Returns a daily summary of Golden Alerts for the last N days (default 30, max 180). Each day's entry includes the total alert count plus a breakdown by severity (high/medium/low) derived from alert confidence scores (≥75 = high, ≥50 = medium, <50 = low), and the top tokens that appeared most frequently in alerts that day. Backfilled from 17 days of real signal_history data (confidence scores from 49,000+ on-chain signals). Data is persisted once per 5-min alert cycle via ON CONFLICT DO UPDATE so each day's entry reflects the latest alert state at last refresh. Days with no data are omitted from the history array. Use ?days=N to control the look-back window (1–180, default 30). Cached 5min. — Use this for daily historical data; use the corresponding live snapshot tool for current conditions and the monthly tool for long-term trends.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
daysNoNumber of recent days to return (1–180, default 30).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
daysNo
totalNo
historyNo
updatedAtNo
dataSourceNo
attributionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "attribution": {
      +      "$ref": "#/components/schemas/Attribution"
      +    },
      +    "dataSource": {
      +      "type": "string"
      +    },
      +    "days": {
      +      "type": "number"
      +    },
      +    "history": {
      +      "items": {
      +        "properties": {
      +          "date": {
      +            "description": "Snapshot date (YYYY-MM-DD, UTC).",
      +            "format": "date",
      +            "type": "string"
      +          },
      +          "highCount": {
      +            "description": "Alerts with confidence ≥75 (high severity).",
      +            "type": "integer"
      +          },
      +          "lowCount": {
      +            "description": "Alerts with confidence <50 (low severity).",
      +            "type": "integer"
      +          },
      +          "mediumCount": {
      +            "description": "Alerts with confidence 50–74 (medium severity).",
      +            "type": "integer"
      +          },
      +          "topTokens": {
      +            "items": {
      +              "type": "string"
      +            },
      +            "type": "array"
      +          },
      +          "totalCount": {
      +            "description": "Total number of Golden Alerts generated that day.",
      +            "type": "integer"
      +          }
      +        },
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "total": {
      +      "type": "number"
      +    },
      +    "updatedAt": {
      +      "format": "date-time",
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
  2. Added

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the description's extra detail is genuinely additive: it discloses the 5-minute refresh cadence, 5-minute cache, omission of days with no data, severity thresholds based on confidence scores, and backfill provenance. No contradiction with annotations exists.

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 main purpose is front-loaded and the structure is readable, but several details are not needed for correct invocation, such as '49,000+ on-chain signals' and the SQL-level 'ON CONFLICT DO UPDATE' implementation. These add bloat even though the overall shape is organized.

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 covers look-back control, data currency, empty-day behavior, severity derivation, and sibling routing, while the output schema handles return-value details. It is nearly complete, but the contradictory max-days value prevents a perfect score because it undermines safe autonomous usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the description adds context about default and range, but it introduces a critical inconsistency: the description says 'max 180' and '1–180, default 30,' while the input schema declares 'maximum': 90. An agent reasoning from the description could issue an invalid request, so the parameter guidance is actively misleading.

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 opens with a specific verb and resource: 'Returns a daily summary of Golden Alerts for the last N days.' It also clearly distinguishes this tool from siblings by positioning it against 'the corresponding live snapshot tool' and 'the monthly tool,' so the agent understands exactly what this history variant provides.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The final sentence gives explicit routing guidance: 'Use this for daily historical data; use the corresponding live snapshot tool for current conditions and the monthly tool for long-term trends.' It also explains the ?days=N look-back control, so when to call this tool versus alternatives is directly stated.

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