Read logcat

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

Annotations say only readOnlyHint=false, so the agent has no explanation of why a 'Read' tool is flagged as mutating – the destructive 'clear' buffer behavior is never mentioned in the description even though it is the reason the read is not safe. It does add useful behavior for 'package' (resolves the current PID) and 'crashesOnly' (crash buffer, uncaught exceptions/ANRs), which is genuine context beyond the annotations.

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?

Two short sentences, front-loaded with the core read action and then the filter options and the crash-buffer shortcut. Nothing is wasted, though it is dense enough that the destructive 'clear' path has no room.

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?

There is no output schema, and the description says nothing about the return shape (raw log lines, ordering, whether truncation occurs at the 5000-line cap). With 8 optional parameters and a mutating flag, the definition is adequate but leaves an agent guessing about results and side effects.

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 88%, so the baseline is 3; the schema already describes tag, grep, clear, lines, serial, package, crashesOnly and minPriority. The description adds only two semantic nuggets (package uses the app's current PID, crashesOnly targets the crash buffer) and never mentions minPriority or serial handling.

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 ('Read recent device logs') and enumerates the filter axes, so the agent knows exactly what this returns. It does not differentiate from the closest sibling (adb_shell), which could also surface log output, but the purpose itself is unambiguous.

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 sentence 'Use crashesOnly to get the crash buffer' is real conditional guidance, and the filter list implies when each parameter applies. However, there is no 'when not to use this' direction, no pointer to adb_shell for non-log shell output, and no statement of prerequisites such as an online device.

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