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

With no annotations provided, the description carries the behavioral burden. It discloses that recording is ongoing ('over time') and that it must be stopped, which is useful. However, it does not mention what happens on repeated starts, whether recording is exclusive per device, or how data is retrieved after stopping.

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 sentences with no filler. The core action is front-loaded, and the stop instruction is a useful second sentence. The analogy 'like screen recording, for metrics' is brief and aids understanding without bloating the description.

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 is adequate for a simple start tool but lacks some context an agent may need: there is no mention of how results are obtained (presumably from the stop tool), whether only one recording can be active, or any caveats about starting multiple recordings. With no annotations and no output schema, this is a notable gap.

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 description coverage is 100%, so the parameters are already documented in the input schema. The description adds only high-level context ('per-process CPU/memory') that loosely maps to the pkg parameter, but provides no additional semantics beyond 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 states a specific verb ('Start') and resource ('recording per-process CPU/memory over time'), which makes the tool's function immediately understandable. It also explicitly names the companion stop tool, helping distinguish it from the lifecycle sibling.

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 clearly indicates the pairing with android_performance_record_stop, giving basic lifecycle guidance. However, it does not mention when to use this tool instead of android_performance_snapshot or other performance tools, so alternative selection is left to inference.

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