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

Annotations already declare a safe read, but the description goes well beyond them: it defines volatility as annualised and forward-looking, defines "bad month" as 1% expected shortfall (average of worst outcomes, not a floor), and warns the 0-10 level is a proprietary scale comparable only within this platform and is not the PRIIPs SRI nor a suitability judgement. That is exactly the interpretive context an agent needs to avoid misusing the numbers.

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?

Front-loaded with the core statement and the sibling routing, then the caveats, then the parameter detail — a sensible order. It is long for a three-parameter tool, but nearly every sentence disambiguates a concept an agent could otherwise misreport (shortfall, proprietary scale, factor vs source).

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 does describe the return shape at a high level (figures, plus per-part volatility shares when `breakdown` is set), and it covers the conceptual semantics thoroughly. It could be slightly more explicit about what the base figures are (volatility figure, risk level, bad month) and about the portfolio_id/holdings exclusivity, which is only implied.

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 only 33%, so the description must carry weight, and it does for `breakdown`: it explains that contributions are ordered largest-first and enumerates holding, group, 'source' (market, countries/currencies, industries, style factors, specific) and 'factor' (named style factors beside other sources' totals). The `holdings` parameter is covered by the schema, but `portfolio_id` is never mentioned in either place, and 'group' is not mapped explicitly to the schema's asset_class/country/sector/industry enum values.

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 precise verb+resource: measures how risky a strategy is from its current holdings, returned as figures without a widget. It explicitly contrasts itself with `open_dashboard(..., tab='risk')` and with the risk tilt in `describe_portfolio_fundamentals`, so an agent can separate it from those siblings without opening a 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?

"For comparing strategies or checking a level against a target" gives a clear usage context, and it names `open_dashboard` as the visual alternative for the same data. It stops short of explicit when-not-to-use conditions (e.g. historical track-record analysis), but the historical-vs-forward-looking caveat effectively covers that.

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