Skip to main content
Glama
Alpha Sentinel Market Intelligence MCP

Alpha Sentinel Market Intelligence MCP

analyze_volatility

Read-onlyIdempotent

Detect unusual cryptocurrency price movements with Z-score anomaly detection, configurable time windows, and threshold-based alerts to spot volatility before trends become obvious.

Instructions

Analyze price volatility using statistical Z-score anomaly detection.

Calculates standard deviations from mean price to detect anomalous movements. Configurable thresholds and time windows for customized analysis.

Use Case: Identify unusual price movements before they become obvious trends.

Cost: $0.02 USD per call

Parameters:

  • symbol: Crypto symbol to analyze

  • window_minutes: Historical window (1-1440 min, default: 60)

  • z_threshold: Std dev threshold for anomalies (0.1-5.0σ, default: 2.0)

Alert Levels: NORMAL → MODERATE → HIGH → CRITICAL

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": {
      "symbol": "<symbol>"
    },
    "name": "analyze_volatility"
  }
}

Input Schema

NameRequiredDescriptionDefault
symbolYesCryptocurrency symbol
z_thresholdNoZ-score threshold for anomalies
window_minutesNoAnalysis window in minutes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered and the description's bar is lower. The description still adds genuinely non-structured behavior: a per-call cost of $0.02 USD and the discrete alert-level scale (NORMAL → MODERATE → HIGH → CRITICAL) that the caller will receive. It stops short of saying how many anomalies or data points come back, but the cost disclosure is real added value beyond the annotations.

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

Conciseness4/5

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

The definition is well front-loaded: purpose and method in the first sentence, then mechanics, use case, cost and parameters in labeled blocks. The parameter bullet list duplicates the schema slightly and the alert-level arrow chain is decorative, but nothing is long-winded or buried.

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 read-only three-parameter analytical tool with no output schema, this covers the essentials: what is computed, the threshold and window knobs, expected alert-level output, and the cost of invoking it. The remaining gap is that it never describes the shape of the result (per-anomaly records vs. a single current score), which matters for a time-windowed analysis.

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 symbol, z_threshold and window_minutes with their ranges and defaults are already fully documented. The description restates the same ranges and defaults ('1-1440 min, default: 60', '0.1-5.0σ, default: 2.0') and adds only mild interpretive framing ('Std dev threshold for anomalies', 'Historical window'). That is baseline support, not meaning beyond the schema.

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 names a specific verb and resource ('analyze price volatility') plus the exact method ('statistical Z-score anomaly detection'), which cleanly separates it from siblings like fetch_price (raw price retrieval) or calculate_risk_score (composite scoring). An agent can pick this tool without opening the schema.

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 'Use Case' line gives a clear motivating context ('identify unusual price movements before they become obvious trends'), which tells the agent when the tool is valuable. However, it offers no when-not guidance and does not name any alternative or complementary tool, leaving the agent to infer the boundary with fetch_price and the risk/report siblings.

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