Rolling volatility

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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered. The description adds real behavioural value beyond that: local DuckDB computation, omission of rows before the window fills, the reporting point (window's last observation), the fraction-per-year unit convention, and that large outputs are persisted as a result_id.

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?

A single dense paragraph that front-loads the core computation and formula, then edge behaviour and units. It is information-rich, though the periods_per_year mapping and return_kind notes duplicate schema text and could be trimmed.

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?

With no output schema, the description supplies the missing return semantics: annualised fraction units, per-window reporting point, and result_id persistence for large outputs. Only minor gaps remain (no mention of error conditions or empty-series behaviour), so it is nearly complete for a read-only analytics tool.

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 100%, so the schema already documents window bounds, result_id format, return_kind enum, and column defaults; that sets a baseline of 3. The description adds marginal framing (window as rows of returns, return_kind ignored for returns results) but largely restates the periods_per_year mapping already present 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?

States a specific verb+resource (computes rolling annualised volatility per series over a stored result) and pins down the exact formula, scope, and input source. It also distinguishes itself from the sibling analytics_returns by clarifying it can consume that tool's output.

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 makes clear the tool operates on a stored result of prices, or on returns produced by analytics_returns, which routes the agent to the right upstream tool. It stops short of explicitly stating when to prefer this over sibling analytics like beta/correlation/drawdown, so it is clear context without exclusions.

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