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

Annotations cover readOnly=false and destructive=false, and the description adds meaningful behavior: with repair, fixes are applied in place and each is kept only if KiCad counts nothing worse — a rollback/guard semantic the annotations cannot express. It omits the return/report format and whether the board must be routed/complete first.

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 core purpose, and every clause carries substance (checks, conditional execution, repair behavior). It is dense and somewhat run-on as one long sentence plus a repair paragraph, but nothing is wasted.

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 3-param check tool with no output schema, the description covers what is checked, when checks fire, and repair semantics. The main gap is the shape of the returned findings/report, though job-follow behavior is already documented in the wait_s schema field.

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 67%, with wait_s and design_id documented in-schema; the undocumented repair flag is the one the description explains best, detailing exactly what gets fixed (track width, skew meanders, return vias, widened rails) and the acceptance condition. It adds real meaning beyond the schema for the one gap.

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 ('Judge the copper by physics') and then enumerates the exact checks performed: impedance from stackup, IR drop/heating, skew, ground-via at layer changes, 3W spacing, via path under paddles. It also positions itself against siblings by naming what KiCad's DRC does not catch and noting finish_board runs the same repairs.

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?

Explains the selection condition 'each check runs only when the board states something it can judge' and clarifies the repair branch versus finish_board, which runs the same repairs. It implies run_drc handles standard DRC but does not state an explicit when-not-to-use case.

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