risk_var

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

With no annotations, the description carries full burden. It explains VaR and CVaR meaning but does not specify return format (e.g., object with two fields) or edge cases like insufficient data. The description provides adequate but incomplete behavioral context.

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?

The description is a single, front-loaded sentence that efficiently conveys key information. It could be slightly more concise by removing the parenthetical translations, but overall it is well-structured.

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?

For a complex statistical tool, the description covers method and interpretation but lacks output schema and does not specify return structure (e.g., whether both VaR and CVaR are returned). This gap reduces completeness.

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% with descriptions. The description adds value by explaining the concept behind the confidence parameter (e.g., VaR(95%)) and the non-parametric method applied to returns, going beyond schema definitions.

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 the tool computes VaR and CVaR using historical simulation, a non-parametric method suitable for fat-tailed crypto returns. It distinguishes itself from sibling risk tools like risk_drawdown and risk_sharpe by specifying the methodology and interpretation.

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 implies usage for crypto due to fat-tail suitability but lacks explicit guidance on when to use this tool over alternatives like risk_drawdown or risk_sharpe. It does not provide criteria for appropriate use cases or exclusions.

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