as_logcat_watch_start

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

The description discloses that it starts a background capture and returns a watch_id, which is useful. However, it does not mention the default behavior of clearing the log buffer (clear_first defaults to true), which is a significant behavioral detail. Annotations do not contradict the description, but this omission reduces transparency.

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 very concise: one sentence for purpose, one for workflow, one for args, one for returns. It is front-loaded with the core purpose and structured logically, with no wasted words.

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?

Given the complexity of starting a background watch, the description adequately explains the workflow and return format (watch_id and offset). It could be more complete by mentioning that the watch runs until explicitly stopped and that serial defaults to the only connected device, but it is sufficient for selecting and invoking the tool.

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 description lists the parameters (serial, filter_spec, clear_first) in a concise 'Args:' line, but the input schema already provides descriptions for these nested properties. The description adds no new format, defaults, or constraints beyond what the schema states, despite low top-level schema description coverage (0%). It marginally compensates by listing them.

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 states 'Start a background logcat capture you can poll incrementally', clearly specifying the verb (start), resource (logcat capture), and mode (background, poll). This differentiates it from siblings like as_adb_logcat (one-shot) and as_logcat_watch_read/stop (subsequent steps).

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 explains the workflow: returns a watch_id, then use as_logcat_watch_read to poll and as_logcat_watch_stop to stop. This gives clear context but does not explicitly state when to use this over alternatives like as_adb_logcat, or exclude cases like needing a raw dump.

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