risk_metrics

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

Annotations already declare readOnlyHint and openWorldHint, so the description's job is lighter and it delivers: it enumerates the full metric set returned, notes benchmark currency conversion, specifies the Bloomberg-style beta convention (2y weekly, 0.67 raw + 0.33 adjusted) and the Morningstar-style monthly capture. Missing: data source/rate limits or behavior for invalid or delisted tickers, which is the main residual gap.

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 purpose in the first sentence, then outputs, then the conditional benchmark branch, then parameter conventions. Dense but every sentence adds information; the middle output-enumeration sentence is long but each metric name earns its place since no output schema exists.

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 compensates by enumerating return values and clarifying the benchmark-conditional extras. Five parameters are largely covered, defaults for period are implied, and the only meaningful gap (confidence semantics) is minor for a read-only analytical call.

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 0%, so the description must carry the load, and it documents 4 of 5 parameters well: period enumerates all valid values (1y, 2y, 3y, 5y, 10y, max), risk_free_annual gives the decimal convention (0.03 = 3%), benchmark explains its effect and currency handling, and ticker is implicit in the opening sentence. The 'confidence' parameter (default 0.95) is never mentioned, leaving its role in the VaR/ES computation undocumented.

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-scope ('risk and performance of one security or index') and the data source ('daily total-return prices'), which distinguishes it from siblings like fundamental_ratios or peer_comparison that operate on accounting or comparison data. It does not explicitly name an alternative, but the resource and computation type are unambiguous.

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?

Usage is implied rather than stated: an agent can infer it should pass a ticker for a single-asset risk report, and the benchmark sentence describes a conditional mode (add a benchmark to get beta/alpha/capture). There is no explicit when-to-use/when-not, and no naming of sibling tools such as technical_indicators or etf_analysis that might also be candidates.

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