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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the agent knows this mutates state. The description adds the eligibility states, but does not say whether the rollback is reversible, what happens to live traffic or decisions, or whether it requires elevated permissions beyond the schema's superadmin hint. With annotations carrying the safety profile, partial credit for the state qualifier.

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?

A single front-loaded sentence with no filler or repetition. The eligible states are embedded efficiently without bloat.

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?

Adequate minimum for a 2-param destructive mutation: purpose and eligible states are clear, and the destructive hint is covered by annotations. However, no output schema exists and the description says nothing about the result of a rollback or recovery options, leaving gaps for a destructive operation.

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 coverage is 100%, so both parameters are documented, including the superadmin-only customerId. The description adds no syntax or format details beyond the schema, so baseline 3 applies.

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?

States a specific verb (roll back) and resource (production A/B test), and qualifies the states it applies to (running, decided, inconclusive). It is distinguishable from siblings like promote_production_test or start_production_test by its verb, though it does not name the inverse tool explicitly.

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 phrase 'running, decided, or inconclusive' implies which test states are eligible for rollback, which is useful qualifier context. But it never states when to prefer rollback vs. alternatives such as promote_production_test, nor does it spell out prerequisites or exclusions.

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