Open a serial port or pyserial URL, then start capturing incoming lines in the background for monitoring and debugging.
Open a serial port (or a pyserial URL such as loop://) and start capturing lines in the background.
| Name | Required | Description | Default |
|---|---|---|---|
| baud | No | ||
| port | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full disclosure burden. It usefully reveals that capture runs in the background (a persistent session that presumably lasts until close_port) and that pyserial-style URLs are accepted, but says nothing about exclusivity, resource locking, error behavior on an invalid or busy port, or permission requirements.
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?
A single front-loaded sentence with the core action first and the qualifier in a compact parenthesis. Every clause adds information; nothing is padding.
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 presence of an output schema means return values need not be described, and the background-capture sentence covers the key state change. However, for a stateful connection-opening tool with zero annotation coverage, the description is thin on preconditions, failure modes, and lifecycle (when the capture stops).
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, and it does for only one of two parameters: it clarifies that 'port' accepts pyserial URLs such as loop://. Baud is untouched in the description (its schema entry has only a default of 115200), leaving half the parameter surface unexplained.
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 (open a serial port) plus a distinguishing behavioral detail (starts capturing lines in the background). It clearly separates itself from close_port, list_ports, and probe_stlink by naming the open action, though it never explicitly names an alternative.
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?
No when-to-use guidance is given: the description does not say to call list_ports first to discover a valid port, does not explain what happens if the port is already open, and does not mention that read_lines/write_line depend on this call. Usage is only inferable from the tool name and sibling set.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.