ui_events

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

The description mentions 'bounded' and 'selector-scoped' but does not disclose side effects, whether events are persistent, or requirements (e.g., running UI session). With minimal annotations, the description should provide more behavioral context.

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?

Single sentence is concise but too sparse for a complex tool. It front-loads the key actions but omits essential details, sacrificing clarity for brevity.

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 9 parameters, no output schema, and no enum hints, the description is grossly incomplete. An agent cannot infer how to specify the selector (e.g., via root_id/xpath) or interpret return values.

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 0% and description does not explain any of the 9 parameters. 'action' and 'buffer_id' are required but their allowed values are not specified. Parameters like 'fields', 'automation_id', 'root_id' are unexplained, making correct invocation unlikely.

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 clearly identifies the tool as managing a 'bounded selector-scoped UI event buffer' with three actions (start, read, stop). It distinguishes from sibling tools that perform individual UI actions. However, it lacks definition of 'selector-scoped' and what events are captured.

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?

No guidance on when to use this tool versus alternatives like ui_query or ui_snapshot. No prerequisites or context provided for starting/reading/stopping a buffer.

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