Starts background high-rate VBUS/IBUS sampling at selectable rates and optionally logs every sample to CSV for live power monitoring and later analysis.
Start high-rate VBUS/IBUS sampling in the background (2, 10, 50 or 1000 samples/s).
Optionally writes every sample to csv_path. Use stream_status / stream_samples while running and stream_stop for the final statistics (energy, charge, min/max/mean).
| Name | Required | Description | Default |
|---|---|---|---|
| csv_path | No | ||
| rate_sps | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the full burden. It does add real behavioral value — the operation is asynchronous ('in the background') and has an optional side effect writing every sample to csv_path — but says nothing about behavior if a stream is already active, buffering/drop characteristics at 1000 sps, or whether the CSV is appended or overwritten.
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 sentences, front-loaded with the core action and rate domain, then the optional side effect, then the companion-tool routing. No filler.
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?
With no annotations and no output schema, the description should cover start/stop semantics and failure modes; it covers the start and hands off to siblings for status and results, but leaves the agent guessing about re-entry behavior and whether data persists if the stream is never stopped.
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 coverage is 0%, so the description must compensate, and it largely does: it enumerates the allowed rate values (2, 10, 50, 1000 sps) matching the enum and explains csv_path as an optional per-sample CSV sink. It still doesn't state the CSV format or whether the file is truncated on start.
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 high-rate VBUS/IBUS sampling in the background') with concrete rate options, so the agent knows exactly what the tool initiates. It is clearly distinct from stream_status/stream_samples/stream_stop, but never contrasts itself with the sibling 'measure' (single-shot) or 'pd_capture_start', so full sibling differentiation is incomplete.
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?
Gives explicit lifecycle routing: use stream_status / stream_samples while running, and stream_stop to collect final statistics. What's missing is when to choose this over 'measure' or 'pd_capture_start', and whether a stream must be stopped before starting another.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.