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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely new behavior: the null-request default runs a shipped synthetic example, real data requires permission, and rights_confirmed is a declaration that does not verify a licence. That last caveat is exactly the kind of non-obvious caveat annotations cannot express. It stops short of 5 because it says nothing about cost, runtime, or limits at the 1,000,000-obligor ceiling.

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?

Two dense sentences with the model/objective front-loaded and the invocation rules following; no filler. The phrasing 'Omit the request to run the shipped synthetic example instead' is slightly compressed and could be read twice, but it is not wasteful.

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 annotations handle the safety profile. The description covers the two things an agent cannot infer elsewhere: the null-request default and the permission/rights gate. Remaining gaps are interpretive details (units, what confidence and horizon mean for the VaR figure) rather than invocation blockers.

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 carries the burden. It fully explains rights_confirmed and clarifies that request is optional (synthetic default), which maps onto the data_mode enum. However, the seven required fields inside AsrfRequest (as_of, source, currency, confidence, horizon_days, obligors, and the obligor-level pd/lgd/correlation) get no semantic treatment in the description — their meaning is only inferable from field names and JSON Schema constraints.

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 model and metric set ('Vasicek asymptotic single risk factor credit VaR, expected and unexpected loss'), so an agent knows this computes an ASRF capital/VaR figure rather than a copula or historical simulation. It implicitly separates itself from risk_credit_copula via the model name, but never explicitly states the contrast, so it falls short of a 5 on sibling differentiation.

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 operating guidance: omit the request to run the shipped synthetic example, and for supplied data set rights_confirmed=true under a permission requirement. What's missing is when to prefer this over the other credit-risk siblings (e.g. risk_credit_copula) — no exclusions or comparative conditions are stated.

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