add_trace

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

Beyond the annotations, it discloses rejection semantics precisely: an invalid net number is refused, nothing is written, and the same applies to any nonzero net on KiCad 9-format or older boards without a net table. It also explains the KiCad 10 name-derived net numbering quirk that makes stale net numbers dangerous, which is exactly the kind of non-obvious behavior an agent cannot infer from readOnlyHint=false alone.

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?

The purpose is front-loaded in one sentence and each subsequent line corresponds to a parameter, so nothing is padding. Points off for the raw docstring "Args:" formatting and for the net explanation, whose clause "and so is every number but 0 on a board in KiCad 9's format or older that has no net table" is dense enough to require re-reading.

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 an eight-parameter mutation with no schema descriptions, the description covers nearly everything an agent needs, and an output schema exists so return values need not be explained. Remaining gaps: coordinate units for x1/y1/x2/y2 are unstated (only width is marked mm), and there is no note that layer must be a valid copper layer from list_pcb_layers.

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% — properties carry only titles — so the description must carry the full burden, and it does: every one of the eight parameters is given meaning, including width units (mm), layer examples ("F.Cu", "B.Cu"), the net=0 sentinel, and that pcb_path is optional with a configured default.

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 first line states a specific verb and resource with scope: "Add a trace segment between two points." Combined with the parameter list (layer, net, width) an agent can tell this is a PCB copper routing primitive, distinct from schematic-side siblings like add_wires or generic add_pcb_line. It stops short of naming which sibling to prefer when the goal is a line rather than a net-assigned trace.

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?

Usage is implied through prerequisites rather than stated: net numbers must come from list_pcb_nets, and on KiCad 10 boards list_pcb_nets must be re-read after each edit. That is real workflow routing, but there is no explicit when-to-use/when-not framing against alternatives such as add_via for layer transitions or add_pcb_line for non-copper geometry.

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