Watch Device Events

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

No annotations are provided, so the description must carry the full burden. It reveals that the tool collects specific event kinds over a duration (max 30 seconds) and mentions a 'kinds' filter. However, it omits key behavioral details: whether the tool blocks, how events are returned (streaming, batch, pagination), what 'screen content' entails (screenshots? OCR?), and any permission or rate-limit concerns. For a monitoring tool, this is a significant transparency gap.

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 a single, concise sentence that front-loads the main purpose and key constraints (duration, kinds). The use of backticks for literals is acceptable, though slightly cluttered. Every clause adds information; there is no filler. However, it could be more structured by separating the kinds list from the general behavior.

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?

Despite an output schema existing (not shown), the description does not explain the output format, how events are aggregated, or whether the tool is synchronous. For a tool that monitors changes over time, an agent needs to know if it will receive a list, a stream, or a summary. Without annotations and with minimal description, the agent cannot predict the tool's full behavior, making it incomplete for safe invocation.

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%, so the description must compensate. It explains the 'kinds' filter values (foreground, keyboard, screen, notifications) and notes that duration has a max of 30 seconds. However, it does not explain the 'device' parameter (which device? default?) or 'interval' (polling frequency? meaning?). Thus it partially compensates for the schema gap but leaves two parameters underdocumented.

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 states the tool's function: collecting changes over a duration, listing the specific event kinds (foreground app, keyboard, screen content, notifications). It uses an active verb 'collect' and specifies the resource (device events). It implicitly distinguishes from siblings like 'get_screenshot' or 'read_screen' which are point-in-time reads, whereas this is a temporal monitor.

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 description implies usage for monitoring changes over time but does not explicitly contrast with alternatives or state when to prefer it over multiple snapshots. No exclusions are given, but the context of a monitoring tool is clear. A more explicit comparison, e.g., 'use this to track changes instead of repeatedly calling read_screen', would improve this.

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