get_logs

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

Without annotations, the description fully discloses that it returns a classified delta by default and raw lines with level, plus PID scoping and the since_last_action window. It is a read-only operation, which is appropriate. Could mention that response format is defined in the output schema.

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 well-structured with a default behavior paragraph and an Args section. Each sentence adds value; 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 3 parameters, no annotations, and an output schema, the description covers purpose, default behavior, and parameters well. It does not describe output format, but that is handled by the output schema. Slightly incomplete regarding potential side effects or performance implications, but adequate.

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 0%, but the description fully compensates by explaining each parameter: lines (max lines when not scoping to last action), level (minimum priority for raw), since_last_action (scope window). Adds meaning beyond schema types.

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 explicitly states it queries app logcat PID-scoped to the current app, distinguishing default behavior (classified delta) from raw filtered lines with level. This clearly differentiates it from sibling tools like get_map and tap_element.

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 when to use default mode vs raw mode ('With level set') and the role of lines parameter ('when not scoping to the last action'). However, it does not mention when not to use the tool or suggest alternatives.

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