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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description usefully adds that the check runs locally against fabrication limits, but it omits what the result looks like (pass/fail per rule, violation list) and does not address what happens when both pcb_text and project_path are supplied or omitted. It also mentions only 'standard 2-layer or 4-layer' limits while the schema exposes a third `fine_hdi` tier, leaving a gap in the behavioral picture.

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?

A single dense sentence that front-loads the action and the resource, then lists the checked rules; there is no filler. It could have spent a few words on the fab_tier options or return format instead of the parenthetical rule list, but it is efficient.

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?

With no output schema, the description should say what a DFM audit returns (violations, thresholds, pass/fail), and it does not. For a read-only, zero-required-parameter tool with three parameters this is serviceable but leaves the agent guessing about the result shape and the fine_hdi tier.

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%, so the schema documents pcb_text and project_path adequately and the baseline of 3 applies. The description adds no meaning to `fab_tier`: it describes only standard 2-layer and 4-layer limits and never explains what `fine_hdi` changes, nor how pcb_text and project_path interact when both are optional.

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 states a specific verb ('Run a ... DFM rule check') and resource (a `.kicad_pcb` or `.dsn` file) and enumerates the rule families checked (trace width, clearance, via hole diameter, annular ring). It is clearly a rule-checking tool rather than a general parser or router, which implicitly separates it from siblings like analyze_kicad_pcb, but it never names or contrasts those siblings explicitly.

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?

Usage is only implied: an agent can infer this is the tool for checking manufacturability before fabrication. There is no statement of when to prefer it over analyze_kicad_pcb or analyze_specctra_dsn, and no prerequisites or when-not conditions are given.

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