backtest_var

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

Mentions no look-ahead, required data length, and demo portfolio behavior. However, with no annotations, it lacks details on side effects, permissions, or error handling.

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?

Three sentences with no redundancy; essential information is front-loaded and each sentence adds value.

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?

Lacks output description for the backtest results (e.g., what the tests return). With no output schema, this is a notable gap.

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?

Explains method values ('historical' or 'parametric'), window in context of data requirement, and returns usage. But alpha is not described despite 0% schema coverage.

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 identifies the tool as a walk-forward VaR backtest with specific statistical tests and the Basel traffic-light zone. It uses strong verbs and distinguishes from siblings like compute_var_es and stress_test.

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?

Provides a prerequisite (needs > window+30 observations) and a shortcut (omit returns for demo portfolio), but does not explicitly contrast with sibling tools or state when to use this over alternatives.

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