pcb_fix

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

With no annotations, the description carries the full burden, and it delivers: it explains the dry-run vs edit behavior ('With write=true it edits the board'), the automatic re-run of DRC, and the self-protective file restore if any non-silkscreen result changes. It also notes footprints are never moved and KiCad must be closed.

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 dense sentences carry the action, scope, safety behavior, and precondition with no filler. The most important facts (what and when) are front-loaded, and every sentence adds information.

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?

The description is strong on high-level behavior and safety, but incomplete for invocation because it omits the meaning of the required 'board' parameter and 'min_size'. Since there is no output schema or annotation support, these gaps are not filled elsewhere.

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 0% and the description only clarifies one parameter's effect ('write=true'). It never explains what the required 'board' field should contain (path vs content) or what 'min_size' controls, leaving the agent to guess at important input semantics.

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?

The description names a specific verb ('Move') and resource ('reference designators flagged by DRC...' on the board), and explicitly states what it does not do ('Never moves footprints'). This clearly distinguishes pcb_fix from the schematic-focused siblings like sch_fix and from pcb_lint, which detects rather than fixes.

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?

The description implies when to use it: after DRC flags reference designators, and emphasizes the write=true dry-run/edit split. It also gives a hard prerequisite ('KiCad must be closed'), but it does not explicitly name alternatives or state when not to use this tool.

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