record

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals notable behaviors: long Android recordings may return multiple artifacts, HarmonyOS supports whole-screen recording on physical devices, and the operation times out after 90 seconds. It does not detail every side effect, but the disclosed traits go beyond the basic start/stop functionality.

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?

The description is compact, front-loaded with the primary action, and uses only three sentences to convey the core function plus key caveats. No filler or redundancy is present.

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 a 22-parameter tool with no annotations, the description is relatively brief and leaves some operational context unclear, such as how start/stop pairing is expected to work and what platform selector combinations are relevant. The output schema exists, so return values need not be explained, but the high parameter count and platform-specific behavior warrant a bit more operational guidance.

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 description loosely aligns with parameter semantics by mentioning 'active app session' and 'selected device', which relate to session/device selectors, and 'start or stop' maps to the action enum. However, it adds no meaning for important parameters like fps, path, quality, or recordingScope, and schema coverage is 73%, so the description does not substantially compensate for the undocumented parameters.

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 uses a specific verb pair, 'Start or stop', and a clear resource, 'screen recording', which distinguishes it from sibling tools like screenshot. Stating the scope as 'active app session or, where supported, the selected device' further clarifies what the tool acts on.

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 gives useful context about platform support and timeout behavior, but it does not explicitly state when to use this tool versus alternatives such as screenshot or replay. The usage is implied rather than spelled out with clear when-to-use/when-not-to-use guidance.

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