pcb_create_net_class

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

No annotations are provided, so the description carries the full burden. It does disclose the meaningful upsert semantics (creates the class if absent, otherwise adds nets) and the active-document dependency, which is genuinely useful. However, it is silent on error behavior for unknown net names, whether existing class membership is preserved or replaced, and whether a new class gets default rules/clearances.

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 lead sentence front-loads the action and its upsert nuance, then Args/Returns are scoped and tight with no filler. The Returns block is partially redundant with the output schema, but it is short enough not to be wasteful.

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 simple two-parameter PCB mutation on the active board, the definition gives enough to invoke correctly: target context, encoding of both parameters, and the create-vs-append behavior. What remains missing is failure/validation behavior and the absence of a 'use pcb_get_net_classes first' hint, both of which matter for a mutate operation with no annotations.

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% — both properties are bare title-only strings — so the description must do all the work, and it largely does: the name parameter gets purpose plus two realistic examples, and nets gets its encoding (comma-separated) plus the "VCC,GND,3V3" example, which is essential to call this correctly. It stops short of stating whether net names are validated or case-sensitive, keeping it at 4.

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 ("Create a net class") on a scoped target ("the active PCB") and clarifies the upsert behavior by noting it can also add nets to an existing class. It does not name or disambiguate against siblings like pcb_get_net_classes or pcb_create_nets_from_list, so an agent must infer the boundary, but the core purpose 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?

Usage is only implied: the agent learns it creates classes or appends nets, and that it operates on the active board. There is no statement of prerequisites (must nets already exist?), no when-not case, and no pointer to pcb_get_net_classes for inspection or pcb_create_nets_from_list for bare net creation.

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