capture_start

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

The description adds meaningful behavior beyond annotations: the capture runs in the background, returns a session_id for follow-up reads, and sessions idle for 30 minutes are dropped. This is important lifecycle information that the annotations alone do not provide. No contradiction with readOnlyHint=false or destructiveHint=false.

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 two sentences with no filler. The action is front-loaded, the session_id return is mentioned immediately, and the 30-minute timeout is a compact but useful lifecycle note. Every sentence earns its place.

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?

The description adequately covers invocation, return value, how to consume the capture, and session expiration. Since an output schema exists, the return shape is already specified. The only notable gap is the exact format of the required 'target' parameter, but given the simple two-parameter schema and sibling context, this is a minor omission.

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?

With 0% schema description coverage, the description carries the parameter-semantics burden. It conveys that 'target' identifies a device or gateway and that 'kind' distinguishes device events, device frames, and gateway frames. It stops short of specifying the exact target identifier format, but it provides enough semantic grounding beyond the bare schema.

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 clearly states the action: 'Start a background capture' of a device's events/frames or a gateway's frames. It distinguishes itself from the sibling capture_read/capture_stop/capture_list tools by explaining this is the initiating operation and explicitly points to capture_read for incremental consumption.

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 practical guidance: start a capture, receive a session_id, then 'read incrementally with capture_read.' It also notes the 30-minute idle timeout. It does not explicitly discuss when to use capture_stop or capture_list, but the core read-vs-start distinction is clear.

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