adb_regression_check

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

No annotations are provided, so the description must fully disclose behavior. It mentions the metrics checked and thresholds but omits whether the tool modifies any state, requires special permissions, or handles missing baselines. It does not indicate if it is a read-only operation.

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 concise sentences: first states the main purpose, second enumerates the three regression metrics with default thresholds. No unnecessary words, well-structured for quick comprehension.

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 tool has 5 parameters and no output schema. The description does not explain what the tool returns (e.g., pass/fail, detailed report), which is important for an agent to interpret results. Missing information on return value and error conditions.

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 the schema already documents all parameters with descriptions. The description adds that thresholds are configurable, but this is already implied by the schema's default values and ranges. No additional parameter semantics beyond 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 that the tool compares current performance against a saved baseline and flags regressions in memory, CPU, and jank rate with specific thresholds. This distinguishes it from sibling tools like adb_regression_baseline (which likely creates baselines) and adb_regression_history (which shows history).

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 performance regression testing but does not explicitly state when to use this tool versus its siblings such as adb_regression_baseline or adb_perf_snapshot. No guidance on prerequisites or exclusions.

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