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

Annotations declare readOnlyHint=false and destructiveHint=false, so the write potential is flagged. The description adds real context beyond that: repair mutates the board in place, enumerates what changes (track width, skew meanders, return vias, widened rails), and gives the guard 'each kept only if KiCad counts nothing worse.' It doesn't cover auth or rate limits.

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 long clause list of checks is dense but each item earns its place as a distinct capability, and the conditional-execution caveat and repair semantics are front-loaded after it. No filler sentences.

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?

No output schema exists, and the description covers the checks, the conditional execution rule, and the mutation behavior under repair; the wait_s param covers job follow-up via get_board_job. Return value shape is left implicit, which is a minor gap for a job-based tool.

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%: design_id and wait_s are self-documented, but repair has no schema description. The description compensates by explaining what repair does and its safety condition, adding meaning beyond the bare boolean.

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?

Names a specific verb ('Judge the copper by physics') and enumerates exactly which physics checks run: impedance, IR drop, skew, return vias, 3W spacing, paddle via path. It explicitly distinguishes itself from KiCad's DRC, which is the natural alternative.

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?

Frames usage against KiCad's DRC ('which KiCad's DRC does not') and notes that finish_board runs the same repairs, giving the agent a clear routing signal. It does not state explicit when-not conditions or prerequisites beyond 'the board states something it can judge.'

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