adb_test_step

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

No annotations exist; the description discloses that it captures screenshot and logcat since last step and saves them. However, it omits side effects like file naming, overwriting, or impact on session state, leaving some behavioral aspects unclear.

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 a single, well-structured sentence that efficiently conveys the tool's core functionality without superfluous 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?

The description lacks information about what the tool returns (e.g., success status, file paths). Given no output schema, this omission is critical for an agent to understand the tool's outcomes.

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 100%, and descriptions in the schema are adequate. The tool's description does not add further meaning beyond the schema, such as formatting hints for the 'description' parameter.

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's action: captures a numbered test step via screenshot and logcat, saving to the session directory. This distinguishes it from sibling tools like adb_screencap or adb_logcat, which focus on individual captures.

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 implies use within test sessions but does not explicitly state when to prefer this tool over alternatives (e.g., adb_logcat or adb_screencap). No 'when not to use' or comparison to siblings is provided.

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