Delete vias on a net that violate clearance to pads or other nets' copper, such as stitching vias left after a part moves. Run stitch_vias again to refill.
Delete a net's vias that now violate clearance to a pad (any net) or to another net's copper, e.g. stitching vias left under a part that moved. Run stitch_vias again afterwards to refill.
| Name | Required | Description | Default |
|---|---|---|---|
| net | No | GND |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already carry destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The description goes beyond them by specifying exactly what is destroyed (only vias now violating clearance, to any net's pad or other copper) and by prescribing a recovery step, which is genuinely useful mutation context. It stops short of noting whether results are reported back.
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 sentences with no filler; the deletion scope is front-loaded and the follow-up instruction trails it naturally. Every clause 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?
For a destructive single-parameter tool whose annotations already disclose the safety profile, the description covers what it does, why the vias qualify, and what to run next. Return value / count reporting is unspecified, but with no output schema that 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?
Schema description coverage is 0%, so the single 'net' parameter (default 'GND') is documented only by its name. The description implies the operation is scoped to one net's vias, which adds some meaning, but never clarifies that 'net' selects the target net or that it defaults to GND. Baseline-to-slightly-better.
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 (Delete) and a precisely scoped resource (a net's vias that violate clearance to a pad of any net or another net's copper). The conditional qualifier distinguishes it from blanket removal tools like rip_up and from additive siblings like stitch_vias/add_via.
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 a concrete triggering scenario ('stitching vias left under a part that moved') and an explicit follow-up action ('Run stitch_vias again afterwards to refill'), effectively naming the alternative tool and the sequence in which to use it. Nothing about when to reach for this tool is left to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.