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

No annotations are provided, so the description carries the full burden. It discloses the return format (time-series + summary) and implies statefulness via sessionId. It does not mention side effects like whether the recording is deleted or if errors occur when no active session exists. With zero annotation coverage, this is a moderate disclosure.

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?

A single, well-structured sentence that front-loads the action and includes key return details. No wasted 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?

With no output schema, the description explains what the tool returns, which is essential. For a one-parameter stop tool, this is largely complete. Minor omissions like prerequisites (an active recording) are implied by the sessionId reference.

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?

The schema provides 100% coverage for sessionId, explicitly stating it comes from android_performance_record_start. The description adds no additional meaning beyond the schema, so a baseline of 3 is appropriate.

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 ('Stop'), the resource ('performance recording'), and the return value (full time-series and per-process summary). This clearly differentiates it from siblings like android_performance_record_start (which starts) and android_performance_snapshot (which likely takes an instant snapshot).

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 it is the counterpart to android_performance_record_start, and the schema parameter sessionId references the start tool. However, it does not explicitly mention alternatives like android_performance_snapshot or state when not to use it. The pairing with start makes usage clear enough.

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