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

Annotations already declare the operation as read-only, non-destructive, and closed-world. The description adds substantial behavioral context beyond that: how insufficient_data is handled, that running experiments list every arm, what holdout means, how beatsControlBp should be interpreted, and that verdict.status informs decisions without stopping or publishing anything.

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 appropriately sized given the absence of an output schema and the need to explain several result fields. It is not ideally front-loaded with a clear action statement, but most sentences carry useful meaning.

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?

Because there is no output schema, the description carries the burden of explaining return values, and it does so thoroughly. It is less complete on input parameter semantics and sibling-tool selection, but the output interpretation guidance is strong.

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%, and the description does not compensate for the undocumented widgetId parameter. The project parameter is documented in the schema, but the description adds no input-specific meaning and never mentions either parameter by name.

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 makes clear that this tool reports A/B experiment results for a widget, including per-arm metrics and verdict details. It does not explicitly distinguish itself from siblings like read_widget_results or list_widget_analytics, but the resource and data returned are specific.

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?

There is no explicit guidance on when to use this tool versus alternatives such as read_widget_results, list_widget_analytics, start_experiment, or stop_experiment. The description explains output semantics but leaves tool selection to inference from the name.

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