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

Annotations already declare this a read-only, non-destructive, closed-world call, so the safety profile is covered. The description does add genuine context beyond them: the conversion-counting window ('only at or after the visitor's first exposure'), the result ordering ('running first'), the no-cost note ('Free'), and the verdict-interpretation guardrail.

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?

Dense and largely front-loaded, with the payoff fields listed first and short imperative sentences closing it out. The long field enumeration is justified because no output schema exists, though the opening clause describes return content rather than stating the tool's purpose up front.

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 full burden of describing returns and does so thoroughly, plus annotations cover the safety profile. The remaining gap is the unexplained 'site' parameter and no note on whether results are live versus cached.

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% for two parameters. The description partially compensates for 'key' by explaining the unkeyed behavior (all tests in the workspace, running first), which implies key selects one test. But 'site' is never mentioned, leaving half the surface undocumented in both schema and description.

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 the resource (an A/B test) and enumerates exactly what is read back: per-variant exposure/conversion counts, rates with 95% intervals, chance to beat control, lift, sample ratio check, and the verdict. It is clearly distinguishable from siblings like experiment_create or experiment_close, though the operative verb is implied rather than stated.

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?

'Without a key, every test in the workspace, running first' gives a real usage rule for the keyed vs unkeyed case, and 'Never call a winner the verdict does not' constrains interpretation. However, no alternatives are named (experiment_close, app_experiment_list) and there is no explicit when-not-to-use guidance.

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