capture_start

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

Annotations declare it is a non-readonly, non-destructive, closed-world operation, but the description adds real substance: capture is lossless and timestamped, covers all rx/tx, writes JSONL into captures/*.obcap, and returns both a workspace-relative and absolute path. It still doesn't say how the capture terminates or any storage/overhead implications, so it is good but not exhaustive.

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?

Two dense sentences with no filler, behavior front-loaded and return/chaining details second. The parenthetical path-routing list is compact but slightly crammed, keeping it just under ideal.

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?

There is no output schema, so the description correctly carries the return payload (relative path + abs_path). For a stateful capture-start tool it covers what is captured and how to consume the result, but omits parameter meaning and the lifecycle relationship with capture_stop.

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% for both parameters, and the description never explains session_id (only alludes to 'a session') or the optional note field. With two undocumented parameters, the description fails to compensate for the schema gap.

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 (Start) and resource (lossless timestamped capture of all rx/tx on a session), names the output artifact (captures/*.obcap, JSONL), and is clearly distinguishable from siblings capture_stop and capture_frames.

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?

It gives concrete downstream usage — pass the returned path verbatim to capture_frames, session_timeline, or replay:<path> — which orients the agent on when this tool fits in a workflow. It stops short of stating when NOT to use it or explicitly contrasting with capture_stop/other starting points, so it lacks full alternative routing.

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