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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds context the annotations cannot: the default synthetic fallback when request is omitted, the licensing precondition, and the important caveat that rights_confirmed is a self-attestation rather than actual licence verification. Return format and model-selection behavior are left to the output schema.

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 short sentences, front-loaded with the capability and model list, then the two mode conditions. The telegraphic phrasing ('Omit the request to run...') is dense but not wasteful; no sentence is padding.

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?

An output schema exists, so return values need no explanation, and the licensing/permission contract is well covered. However, for a tool whose nested request holds eight required numeric/date fields with a 0%-described schema, the definition leaves an agent guessing about input expectations beyond the two top-level parameters.

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% and the nested TailRequest carries eight required fields, so the description must carry real weight. It does explain the optionality of request and the meaning of rights_confirmed, but it adds nothing about pnl, confidence, horizon_days, portfolio_value, currency, source or the synthetic vs user-licensed 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?

The description names a specific output pair (VaR and ES) and enumerates the seven model families computed, which tells an agent exactly what the tool returns. The phrase 'side by side' implicitly separates it from the single-model sibling risk_tail, though no sibling is named explicitly.

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 gives explicit invocation conditions for two modes: omitting the request runs the shipped synthetic example, and supplied data requires permission plus rights_confirmed=true. What it does not do is state when to prefer this over risk_tail or other risk siblings, so there is clear context but no exclusions.

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