adb_screenshot_diff

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

With no annotations, the description carries full burden. It discloses pixel-level comparison, tolerance, and reporting details (count, percentage, bounding box). No destructive actions are implied, and the read-only nature is evident.

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 front-load the purpose, followed by process and tolerance. Every sentence adds value without verbosity.

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 no output schema, the description effectively explains the output metrics. It covers the tool's behavior and parameters adequately, though it could mention prerequisites like baseline existence.

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%, so baseline for parameter semantics is 3. The description adds context about tolerance absorbing dynamic elements, but the schema's parameter descriptions are already detailed (e.g., tolerancePercent describes absorbing clock/status bar changes).

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 compares the current screen to a saved baseline, explains pixel-level decoding, and reports difference metrics. It distinguishes itself from siblings like adb_screenshot_baseline by focusing on comparison.

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 usage for visual regression testing by mentioning tolerance for dynamic elements, but lacks explicit when-to-use or when-not-to-use guidance against alternatives like adb_screencap or other screenshot tools.

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