Retry Verdicts

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

With no annotations provided, the description carries the full burden and succeeds: it states the operation is non-destructive, changes no assertions/controls/verdict content, causes no ID churn, runs in the background, and tells the agent to re-read the sufficiency or verification report afterward. This is unusually complete behavioral disclosure.

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?

The description is dense but every sentence earns its place: summary, failure scenario, exact scope, side-effect guarantees, async behavior, and sibling comparison. It is front-loaded with the core purpose and then deepens with necessary details, with no filler.

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 description thoroughly covers the triggering conditions, operation scope, side effects, async execution, and how to observe results. However, the required server_version parameter is never explained, which is a real gap given that the schema also omits its description. The sibling-comparison and output-schema presence mitigate most other completeness concerns.

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 only 50%: model_id has a schema description, but server_version has none. The tool description does not mention server_version at all, so the agent is left guessing what value to supply. The description adds no parameter-level meaning beyond what the schema already provides.

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 opens with a specific verb and resource: 'Re-trigger a model's parked verdict re-evals after a transient failure.' It further clarifies the exact scope — only parked/failed re-eval slots across all verdict kinds — and differentiates itself from the sibling recompute_verdicts by naming the alternative and explaining the difference.

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?

The description gives an explicit when-to-use rule: 'Prefer this over recompute_verdicts when verdicts are stuck due to an outage.' It also lists the triggering conditions (provider outage, exhausted credits, timeout) and explains what recompute_verdicts cannot do, making the choice between siblings unambiguous.

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