Skip to main content
Glama

risk_kelly

Read-onlyIdempotent

Calculate optimal position sizing using the Kelly Criterion in discrete or continuous modes. Input win/loss probabilities or historical returns to determine bet fractions that optimize long-term growth.

Instructions

Kelly Criterion: discrete (win/loss) or continuous (returns series) mode.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNoCalculation mode: discrete (win/loss) or continuous (return series)discrete
win_rateNoProbability of winning (0-1), required for discrete mode
avg_winNoAverage win amount, required for discrete mode
avg_lossNoAverage loss amount (positive number), required for discrete mode
returnsNoArray of historical returns, required for continuous mode
Behavior3/5

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

Annotations already declare readOnlyHint=true and idempotentHint=true. The description adds useful context mapping 'discrete' to win/loss scenarios and 'continuous' to return series analysis, but doesn't explain what the tool returns (optimal fraction to bet) or validation logic implied by the parameter descriptions.

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?

Extremely concise at 10 words. The single sentence is front-loaded with the core concept (Kelly Criterion) and mode distinctions. While efficient, it borders on too terse for users unfamiliar with which mode applies to their use case.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the rich schema (100% coverage, clear parameter descriptions), the description doesn't need to detail parameters. However, for a financial calculation tool, it omits what the output represents (optimal betting fraction) and doesn't clarify the mutual exclusivity of parameter groups (discrete vs continuous inputs) beyond the mode parameter description.

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?

With 100% schema description coverage, the baseline is 3. The description adds minimal semantic grouping by mentioning the two modes parenthetically, but doesn't need to compensate for schema gaps since all parameters are well-documented in the schema itself.

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 identifies the tool calculates the Kelly Criterion and specifies the two supported calculation modes (discrete vs continuous). However, it doesn't explicitly state that this is for optimal position/bet sizing or distinguish it from the sibling 'risk_portfolio' tool.

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

Usage Guidelines2/5

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

No explicit guidance on when to use discrete mode (win/loss probabilities) versus continuous mode (return series), nor when to prefer this over the sibling risk_portfolio tool. The description only labels the modes without explaining selection criteria.

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/QuantOracledev/quantoracle'

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