A/B test details and results

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

Annotations already declare readOnlyHint=false, openWorldHint=true, destructiveHint=false, matching the implicit fact that a call can rotate variants and recompute results. The description adds useful behavioral context about data freshness and lag. It does not explain the side effects of rotation, whether results are cached, or any permission requirements.

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 compact sentences: the first front-loads the payload contents, the second front-loads the reliability and lag caveat. Dense and waste-free, though it reads as a noun-phrase fragment rather than a complete statement of the action.

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?

With no output schema, the description carries the return-shape burden and does it well by naming the metrics returned and the verdict. For a 2-parameter read/detail tool this is nearly complete; only the required test_id semantics and any error/permission behavior are 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 coverage is only 50%, and the undocumented parameter is the required test_id, which the description never mentions or explains (format, where to obtain it). The refresh parameter is fully described in the schema but also absent from the description, so the description adds no meaning beyond the schema.

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 enumerates exactly what the tool returns for a single A/B test: schedule, live variant, per-variant daily averages, lift, p-values, and verdict. Combined with the title, an agent can tell it retrieves details/results for one test. It does not distinguish itself from list_ab_tests or stop_ab_test, so it stops short of a 5.

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 reliability rule ('results become reliable once every version has 3+ clean days') and the ~2-day analytics lag give real guidance on when the output is trustworthy. However, there is no explicit statement of when to call this versus list_ab_tests (find the id first) or stop_ab_test, and no prerequisites are mentioned.

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