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

The annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered and the description does not need to restate it. What the description does add is genuine behavioral context the annotations cannot convey: this is a metered call costing 5 prepaid credits and requiring production billing. It does not disclose what the assessment produces, how confident the verdict is, or what happens when the credit balance is exhausted.

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 short sentences, front-loaded with the core purpose and followed by the billing constraint, with no filler. The all-caps "PAID ONLY" is slightly shouty but is the most decision-relevant fact after the purpose, so it earns its position. Nothing here could be cut without losing information.

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?

There is no output schema, so the description is the only place an agent could learn what an "assessment" looks like — a boolean, a risk score, a recommended action, or a rationale. It says none of that, and with 0% schema coverage it also leaves the parameter formats undefined. For a three-parameter metered tool whose entire value is the returned verdict, the definition is under-specified.

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 and does partially discharge it by glossing the three fields as request method, status and idempotency key. However, it gives no format guidance — whether method is an HTTP verb string, whether status is an HTTP code or an internal code, and what an absent idempotency_key implies for the verdict. The added meaning is directional but not operational.

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 verb ("Assess") and a specific resource ("automatic retries"), and scopes it to the three inputs that drive the verdict. That is enough to separate it from a sibling like privi_retry_schedule, which by name implies configuring retries rather than judging their safety. It stops short of stating what the assessment returns, so the purpose is clear but not fully self-contained.

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?

Usage is implied rather than stated: an agent can infer it should call this when it has a request method, a status and optionally an idempotency key and wants to know whether a retry is safe. There is no explicit when-to-use framing, no when-not-to-use, and no named alternative among the many privi_* siblings. The implied context is adequate but leaves routing decisions to inference.

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