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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=false, so safety is covered. The description adds the session lifecycle fact that recording must be explicitly stopped, but says nothing about rate limits, what happens on a second start, or where metrics surface, so it only modestly extends the annotations.

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 short sentences, no waste, with the core action front-loaded and the stop counterpart as a closing pointer. Nothing redundant.

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 three-parameter start tool with no output schema and annotations covering the safety profile, the description is nearly sufficient. The one small gap is that it does not say where the recorded metrics are retrieved (stop return vs snapshot), which an agent must infer.

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 all three parameters (serial, pkg, intervalMs) are already documented with defaults and bounds. The description adds no syntax or format detail beyond what the schema provides; baseline 3 applies.

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?

States a specific verb ('Start recording') plus the resource and scope ('per-process CPU/memory over time'), and explicitly names the paired sibling android_performance_record_stop, so an agent can place it against the stop/snapshot tools without opening a schema.

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 gives clear context for use (continuous metrics capture) and routes the agent to android_performance_record_stop for termination, which is the essential workflow pairing. It does not, however, distinguish when to prefer this recording over android_performance_snapshot or android_fps.

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