sch_netlist

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is met; the description adds genuinely useful behavior beyond them by disclosing the cache and its invalidation condition ('cached until any schematic file changes') and the root-sheet-export mechanism.

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?

Three tight sentences, front-loaded with what is returned, then provenance/caching, then the one-line value proposition. No filler or restatement of the tool name.

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 values need no explanation, and caching, refresh, and multi-sheet path resolution are all covered. The only real gap is the truncation behavior implied by max_nets.

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 75%, so most parameters are self-documented and the 3 baseline applies. The description elaborates on cache/refresh semantics, but says nothing about max_nets or what happens when the net count exceeds it, leaving that one parameter's behavior opaque.

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 resource (resolved connectivity of the whole schematic hierarchy) and enumerates exactly what is returned: nets with nodes, components, sheets. The closing claim 'source of truth for what connects to what' cleanly separates it from siblings like pcb_net_stats or sch_list_components.

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?

It explains provenance (exported by kicad-cli from the root sheet) and the caching lifecycle, which implies when the tool is appropriate and when refresh is needed, but it never names an alternative (sch_trace, pcb_net_stats) or states when this tool is the wrong choice.

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