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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds real value with the synthetic-default behavior and the permission/rights_confirmed gate, plus the honest caveat that it does not verify a licence. It still says nothing about how supplied rows are aggregated across netting sets or what happens when required fields are missing.

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 with the primary output description front-loaded, then fallback behavior, then the permission condition. No filler; the only mild cost is that the licence caveat is packed densely into the final clause.

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 not be described, and annotations cover safety. What remains missing is guidance on the nested request payload — notably what the data_mode enum values mean and why rows must contain at least two entries — which matters for a tool whose main input is a structured profile.

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 meaning, and it explains the role of both top-level parameters: request is optional (synthetic fallback) and rights_confirmed gates supplied data. However, the rich nested ExposureProfileRequest fields (as_of, currency, source, data_mode enum, rows with minItems 2) get no explanation at all, leaving a substantial gap.

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?

Names the concrete outputs (Peak PFE, EPE, Effective EE, Effective EPE) and the input (a supplied simulated exposure profile), so an agent knows it is a summary-metric tool rather than a raw exposure feed. It does not explicitly contrast itself with the similarly named risk_exposure sibling, which keeps it from 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?

Gives a clear conditional: omit the request to run the shipped synthetic example, supply data plus rights_confirmed=true for real input. That is genuine when-to-use guidance, though it offers no exclusions relative to sibling tools such as risk_exposure.

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