events

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

The description goes well beyond the annotations. While readOnlyHint and idempotentHint already indicate safety, the description reveals concrete behavioral constraints: no follow mode, bounded to 'count' or 'duration' seconds (capped at 30s), and suitability for sync stdio transport. This adds materially to what annotations alone provide.

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 compact and front-loaded with the primary purpose. Every sentence earns its place: the first states the action, the second explains the bounded behavior and the reason for divergence from the CLI version, and the third provides usage context. No fluff or redundancy.

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?

The description is largely complete for tool selection: it covers purpose, behavior, and usage context relative to siblings. The absence of an output schema makes return value description less critical, but a bit more detail on what constitutes a 'typed device event' (e.g., sample events) would make it fully self-contained. The unexplained 'profile' parameter also slightly reduces completeness.

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?

The input schema has 0% description coverage, so the description compensates partially by explaining 'count' and 'duration' semantics ('returns up to count events or duration seconds' worth'). However, the 'profile' parameter remains undefined, with no hint in the description about its role or accepted values, leaving a gap that the schema does not fill.

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 uses a specific verb+resource ('Collect typed device events') and clearly identifies the source (kvmd stream) and nature (read-only, bounded). It also distinguishes itself from the sibling tool 'logs' by framing events as a live typed stream for cross-checking vision waits, which is more than enough to differentiate it from the broader sibling set.

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?

Explicit guidance is given: 'logs is the better first diagnostic; events add the live typed stream... to cross-check a vision wait against' clearly instructs when to use events versus an alternative. It also explains the bounded behavior (count/duration cap) which informs practical usage, satisfying the 'when-to-use' requirement.

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