Read bounded buffered float32 I/Q samples and return a summary with a short preview for receive diagnostics; values are not calibrated RF measurements.
Consume bounded buffered float32 IQ and return summary/preview; not calibrated RF.
| Name | Required | Description | Default |
|---|---|---|---|
| sample_count | No | ||
| preview_samples | No |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations declare destructiveHint=true/readOnlyHint=false, and the word 'consume' explains that reason: the read drains buffered data rather than being a harmless peek. 'not calibrated RF' is genuinely useful context beyond the annotations, warning that returned values have no absolute units. It still omits that a live session is required and what happens when the buffer is empty.
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?
One compact, front-loaded sentence with no filler, and the calibration caveat is placed as a trailing qualifier where it belongs. It is efficient but telegraphic, which is part of why the guidance gaps exist.
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?
An output schema exists, so return structure need not be spelled out, and the annotations cover the safety profile. However, for a hardware-touching destructive read the description never states the session precondition or the drain/empty-buffer behavior, leaving a meaningful gap for the caller.
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 carry both parameters, but neither sample_count nor preview_samples is named or explained. 'Bounded' and 'preview' only loosely gesture at them; units, defaults, and the meanings of the 1-8192 and 0-32 caps are left entirely to the schema titles.
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 gives a specific verb+resource: consume buffered float32 IQ samples and return a summary/preview. That clearly separates it from the sibling connect/disconnect/diagnostics tools. It stops short of naming a sibling or stating the buffer's source, but the action is unambiguous.
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?
There is no statement of when to call this versus rp_rx_connect, rp_rx_disconnect, or the diagnostics tools, and no precondition such as an active connection or a populated buffer. The agent must infer that consumption only makes sense after connecting and that repeated calls drain the stream.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.