finance.var_parametric

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

Annotations already cover read-only/idempotent/closed-world safety, and the description adds substantive behavior: the exact formula, the sign convention (loss reported as a positive number), the 8-decimal precision, and the known bias of underestimating losses on fat tails. That is real predictive context for interpreting the result, not a restatement of annotations.

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?

Four compact sentences that front-load the method before parameters and caveat; every sentence contributes (definition, formula, param rules, limitation). Slightly dense with the formula wedged into the parameter sentence, but no filler.

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 two-parameter read-only calculator with an output schema, the definition covers method, inputs, output sign/precision and the key caveat. The only missing piece an agent might need is the return-convention (simple vs log) that determines whether the z-score math is valid.

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 description coverage is 0%, so the description carries the full burden and mostly does: returns is a list of period-return strings requiring at least two entries, and confidence is a value in (0,1) defaulting to 0.95. The gap is that it never says whether returns are arithmetic or log returns, and does not mention that confidence is typed as a string in the schema.

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 names a specific verb and resource (parametric VaR/CVaR under a normal-distribution assumption) and states the exact estimator (sample mean and sample stdev with n-1). It explicitly distinguishes itself from the sibling var_historical, so an agent can pick the right one without opening either schema.

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?

It states the precondition (normality assumption), the input constraint (returns must have 2+ items, confidence strictly between 0 and 1, default 0.95) and names the alternative to cross-check against when tails are fat. It stops short of an explicit 'do not use this when...' rule, which keeps it at 4.

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