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

Annotations only mark this as a non-read-only, non-destructive mutation, so the description carries most of the burden and delivers real substance: the P-016 rejection for cross-group versions and the non-obvious failure mode where requests omitting context.trafficKey leave the test at 0%. It does not cover what happens if a test is already active or what side effects/return values follow on success.

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?

Four sentences, front-loaded with purpose followed by prerequisites and failure modes; every sentence carries information. The final sentence about trafficKey is slightly dense but still earns its place.

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?

Covers prerequisites, the cross-group rejection, and the traffic-split mechanism, which is strong for a 3-required-param mutation tool with no output schema. Gaps remain around response shape and the behavior when a test is already running, but nothing critical to correct invocation is missing.

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 100% and the schema already documents all three parameters, including the "published version of this group" constraint on testVersionId. The description restates those constraints and adds the trafficKey routing detail, which is behavior rather than parameter semantics, so the baseline 3 holds.

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 and resource ("Start an A/B test on a policy group") and is immediately distinguishable from the adjust/stop siblings by name and opening sentence. An agent can tell what this does without opening the schema.

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?

Gives clear preconditions for use: a challenger version ID and traffic rate are required, and the challenger must be a published version of the same group. It does not explicitly name lexq_ab_test_adjust or lexq_ab_test_stop as the alternatives once a test is running, so routing between siblings is only implied.

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