compute_var_es

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

No annotations are provided, so the description bears full responsibility for behavioral disclosure. It explains the computation methods, input constraints (equal-length return lists, default weights, demo book fallback), and hints at output interpretation (divergence as fat-tail signal). It does not detail return format, but given the tool's computational nature, the description provides sufficient transparency for appropriate use.

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 extremely concise, consisting of three short sentences. The first sentence establishes the core purpose, the second specifies input structure, and the third adds an interpretive note. Every sentence adds value with no redundancy or fluff.

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 moderate complexity (four methods, portfolio inputs) and lack of output schema, the description covers inputs, defaults, methods, and even provides an interpretation hint. It does not describe the return format, which would be helpful, but overall it provides enough context for an agent to understand how to invoke and interpret results.

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?

Input schema has 0% description coverage, yet the description fully explains all three parameters: alpha as confidence level (default 0.99), asset_returns as object mapping asset names to equal-length return arrays, and weights defaulting to equal allocation. It also explains the demo book behavior when both are omitted. This adds substantial meaning beyond the raw schema types.

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 computes VaR and Expected Shortfall by four named methods (historical, parametric-normal, Cornish-Fisher, Monte Carlo) at a specified confidence level. It distinguishes itself from sibling tools like backtest_var, evt_tail_risk, and garch_volatility by focusing on standard VaR/ES computation rather than backtesting, extreme value theory, or volatility modeling.

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 explains the tool's function and input requirements but does not explicitly state when to use this tool over alternatives. It implies usage for portfolio risk measurement but lacks guidance on when to choose this method over other risk tools among siblings. The note about divergence as a fat-tail signal offers some interpretive context but not usage criteria.

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