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

Annotations already declare readOnlyHint, idempotentHint, and a closed-world non-destructive profile, so the bar is lower; the description still adds real value by explaining the null-request default path, the permission prerequisite, and the caveat that confirmation does not verify a licence. It leaves sizing/performance limits (10k positions, 100k scenarios) and runtime cost unmentioned.

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 tight sentences, front-loaded with what the tool computes before the operational caveats. Dense and largely waste-free, though 'require permission' is vague about what permission means and what happens if it is absent.

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 tool with a large nested request schema and an output schema (so return values need no explanation), the description covers the synthetic-vs-supplied routing and the licence caveat but omits the semantics of data_mode, time_mode, and the scenario/position limits. It is adequate for a first call but not complete for correct parameterisation.

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 must carry the load. It fully explains the two top-level parameters — request being optional (null triggers the shipped synthetic example) and rights_confirmed gating user data — but says nothing about the nested request fields (data_mode, time_mode fixed/decay, confidence, horizon_days, minimum of 2 scenarios), whose meaning an agent must infer from field names and enums.

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 computation (historical full-revaluation P&L, VaR and ES) on a specific resource (an options book driven by supplied spot and vol moves), which is enough to separate it from siblings like risk_derivatives_greeks or risk_var_attribution. It stops short of explicitly contrasting with any named sibling, so it sits at a clear 4 rather than a 5.

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 concrete when-to-do-what guidance: omit the request to run the shipped synthetic example, supply a request plus rights_confirmed=true for user data. It does not name alternative tools (e.g. a scenario-based or Greek-only sibling) or state exclusions, so no 5.

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