start_recording

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

With no annotations, the description carries the full burden of behavioral disclosure, yet it only says that recording starts. It does not mention whether the recording must be explicitly stopped, whether starting a recording while one is already active fails, whether permissions are needed, or what side effects occur. The localPath note is forward-looking and not a behavior of this tool.

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 only two sentences and is mostly concise. The first sentence is effective and front-loaded. The second sentence adds relevant workflow advice, though it is arguably misplaced in this tool's description since it refers to stopping rather than starting.

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 tool with no output schema and no annotations, the description leaves out key context: what happens when recording starts, whether a recording handle or identifier is returned, how long recording can run, and what state the device enters. The note about stopping is helpful but incomplete for safe and correct invocation.

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 0%, so the description must compensate, but it does not explain deviceId or platform. The parameter names and the platform enum are somewhat self-explanatory, yet no additional meaning is added. The mention of localPath is actually confusing because localPath is not an input parameter of this tool.

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 action and resource: 'Start screen recording on the device.' This clearly distinguishes the tool from its sibling stop_recording by the verb 'start.' However, the second sentence introduces a localPath concept that belongs to stopping, slightly muddying the focus on this tool's direct purpose.

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: call this when you want to begin capturing the device screen, then later stop with stop_recording. The guidance about an absolute path for localPath when stopping hints at the workflow, but no explicit alternatives, exclusions, or conditions are provided. The usage context is inferable but not clearly stated.

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