analyze_metrics_composite

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

No annotations are provided, so the description must fully disclose behavior. It mentions 'backtest' and 'forward returns at 8 horizons' but lacks details on resource consumption, data time range, or side effects. Without annotations, this is insufficient for safety assessment.

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

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

Two sentences, zero wasted words. First sentence summarizes core purpose, second adds operational details. Perfectly front-loaded and efficient.

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

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

Given the tool's simplicity (2 params, no output schema), the description adequately covers purpose and behavior. It mentions 'forward returns at 8 horizons' to hint at output structure, but lacks details on edge cases or ordering. Still, it's sufficient for a basic understanding.

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

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

Schema coverage is 100%, but the description adds context: conditions are z-score thresholds, require 2-4 items, and must all fire simultaneously. This clarifies the 'conditions' array's purpose beyond the schema's field descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it's a multi-factor z-score intersection backtest, specifying the verb 'backtest' and resource 'metric conditions'. It distinguishes from siblings like analyze_metric (single metric) and backtest_signal (signal-based) by focusing on multiple conditions firing together.

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

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

The description gives clear context: define 2-4 conditions and see when all fire, with forward returns. It implies when to use (multi-factor intersection) and hints at alternatives (single metric or signal backtesting) via sibling tools, but does not explicitly state when not to use.

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