pcb_audit_pad_center_connected

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

No annotations exist, so the description carries the full burden and does so: it declares "Read-only" and lists exactly what is inspected (every netted pad; track/arc/via on the same net reaching the centroid). It does not say what happens to pads on nets with no routing at all, but the read-only guarantee and the check mechanics are the important disclosures.

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?

Front-loaded with the definition, then mechanics, then rationale, then the return shape — no wasted clauses. The explicit "Returns:" block is somewhat redundant given a declared output schema, but it is two lines and aids scanning.

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?

A zero-parameter, read-only audit with an output schema is fully covered: the agent knows what is checked, what is excluded, that it mutates nothing, and what fields each offender carries. Nothing needed to call it correctly is missing.

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?

The tool takes zero parameters, so there is nothing to disambiguate and the baseline applies. The description correctly implies the scan runs over the whole board rather than a caller-specified subset.

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 — find pads with no copper at their centroid — and names the domain term ("acid-pad check"). The added sentence on how it decides (track/arc/via on the same net reaching the centroid) makes it unmistakable versus neighbors like audit_find_bad_connections or audit_find_pads_near_board_edge.

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 clear condition for running it — pads connected only at the edge can fail in fab — and scopes the check to "netted" pads, implying unnetted pads are out of scope. It does not name a sibling audit to run instead when the failure mode is different (e.g. unconnected pins), so no explicit exclusion.

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