start_recording

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

With no annotations, the description carries the full burden; it does disclose two important behaviors: a handle is returned and must be fed to stop_recording, and output is cropped when window_id is given. It omits other material traits such as screen-recording permission requirements, where the video is written, frame-rate implications, and whether starting twice is an error.

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?

Three short, front-loaded lines: the action first, then the return contract, then the conditional behavior. Nothing is padded and each sentence adds information.

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 side-effecting capture tool with no annotations and no output schema, the definition covers the basic lifecycle but not operational prerequisites (permissions, storage location, duration limits) or the meaning of fps. It is adequate to start a recording but not complete enough to predict its side effects.

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. It explains window_id well (cropping to that window), but fps — including its default of 15 — is never mentioned in the description, leaving half the parameters semantically bare.

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 and resource ("Start recording the screen (or a specific window) as video"), which is clearly distinct from siblings like screenshot or stop_recording. It also names the lifecycle partner (stop_recording), though it does not explicitly contrast itself with the single-frame screenshot tool.

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 "Returns a handle to pass to stop_recording" line implies the paired workflow and gives an implicit start/stop contract. However, there is no explicit when-to-use or when-not guidance (e.g., use screenshot for a single frame, or what happens if a recording is already running).

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