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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world, so the safety profile is covered. The description adds non-obvious context the annotations cannot: a permission/rights gate on supplied data and the explicit caveat that the flag is not a licence check. It does not describe magnitude of computation, runtime, or validation failures on the covariance matrix.

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: the computation first, the default/no-argument behavior second, the permission caveat last. Every sentence carries distinct information with no restatement of the name or title.

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?

The tool is complex (nested request object, matrix input, up to 100k positions) but an output schema exists, so return values need not be explained. The description covers invocation mode and authorization but leaves the bulk of the request payload's semantics to field names alone, which is thin for a model that must construct a consistent covariance/asset pairing.

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 ReverseStressRequest exposes roughly a dozen fields (nav, as_of, positions, covariance, target_loss, horizon_days, floors, data_mode, assets, source, currency). The description adds meaning only for the nullable request default and the rights_confirmed flag, leaving key semantics such as loss units, covariance scaling/ordering versus assets, and floors behavior completely 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?

"The most plausible shock under a supplied covariance that produces a target loss" names the specific computation (reverse stress: solve for the shock, given a loss target and covariance), which an agent can distinguish from a forward stress tool. It does not explicitly name or contrast with the sibling risk_stress, so differentiation is inferred from the word "reverse" rather than stated.

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 clear conditional routing: supply a request for real data, omit it to run the shipped synthetic example, and set rights_confirmed=true when supplying data. The exclusions are concrete, but no sibling tool is named as an alternative for forward stress or covariance computation, so the agent must infer that from the catalog.

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