Start log capture

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

With no annotations, the description carries the transparency burden. It discloses background behavior, the returned sessionId, and the app-running prerequisite. However, it does not describe the file handling, how to retrieve the captured logs, or implications of the clear parameter (though schema covers that). More behavioral context, such as what happens when stop is not called, would improve 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?

Three concise sentences convey purpose, return value, and a prerequisite without redundancy. Every sentence earns its place; no filler or unnecessary elaboration.

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?

For a tool with no output schema and no annotations, the description covers core purpose, mechanics, and a key prerequisite. It does not explain how to obtain the captured file or when to prefer this over get_logs, but given the strong schema parameter descriptions, the tool is mostly self-explanatory. A brief mention of the sessionId's role could enhance orientation, but the current level is 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 covers 100% of parameters, so baseline is 3. The description adds a small clarification ('via its pid') and the 'and/or' relationship between appId and tag, but otherwise the parameter details are already well documented in the schema.

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 starts capturing logcat to a file in the background, distinguishing it from siblings like stop_log_capture and get_logs. It specifies a concrete verb ('start capturing') and the resource (logcat to a file).

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?

It provides usage context by mentioning the returned sessionId for stop_log_capture and the prerequisite that the app must be running for appId filtering. It lacks an explicit comparison with get_logs or get_crash_logs, but the background-capture purpose guides selection appropriately.

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