Start a logcat stream

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

Adds lifecycle context the annotations don't carry: the stream is long-lived and is torn down when the server shuts down, which matters for resource management. readOnlyHint=true is not contradicted, since the tool observes logs rather than mutating device state, though holding a persistent process is a resource trait the description handles well.

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?

Three tight sentences with zero filler; the core action and return value come first, followed by the follow-up calls and the lifetime caveat in priority order.

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 no output schema, the description usefully names the return value (stream_id) and the lifecycle that governs it. For a 2-param tool with full schema coverage, that is nearly complete; only the snapshot-vs-stream choice is unaddressed.

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 100%, so both parameters (device, filter_spec) are already fully documented in the schema with examples. The description adds no syntax or format detail beyond that, so baseline 3 applies.

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?

States a specific verb and resource ('Start a long-lived `adb logcat` process on one device') plus the return value (stream_id). It is clearly distinguishable from logcat_snapshot (one-shot) and read_logcat_stream/stop_logcat_stream (lifecycle stages), all of which are named or implied.

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?

Explicitly routes the agent through the lifecycle: poll with read_logcat_stream, release with stop_logcat_stream. It does not, however, state when to prefer this long-lived stream over the sibling logcat_snapshot for a one-time capture, so the main alternative is left implicit.

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