audit_fab_capabilities

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

Annotations already declare readOnly, idempotent, and non-destructive behavior, so the safety profile is covered. The description adds domain context — checks are evaluated against vendor-published process limits and the negative outcome targeted is CAM EQ rejection — but does not describe the result shape (pass/fail per rule, margins) or what happens for unspecified defaults. Useful context, but not rich behavioral disclosure.

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 verb and resource, then lists fabs and checks before ending on the business justification. Every clause carries information and nothing is repeated from the schema, though the parenthetical vendor list and check enumeration make it long for one sentence.

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 establish scope; it does so by naming the rules audited and the fab profiles available. All 7 parameters are optional with documented defaults, and the description implies defaults are applied when omitted. The main gap is the absence of any indication of what the audit returns, but overall this is sufficient for an agent to call it correctly.

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 description coverage is 100% and each of the 7 parameters carries its own unit-labeled description with defaults, so the schema does the heavy lifting. The description adds marginal value by naming derived quantities (annular ring, aspect ratio) not present as inputs, but supplies no syntax, range, or interaction guidance beyond the schema. Baseline 3 is appropriate.

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 precise verb (audit), the resource (PCB layout physical design rules), and the reference set (fab house capabilities with named vendors JLCPCB standard/advanced, PCBWay, OSH Park), then enumerates the exact checks performed (trace width, clearance, via drill, annular ring, aspect ratio, slot width). This distinguishes it from generic siblings like calculate_ipc2221_clearance and audit_ipc6012_class_compliance, which target standards rather than vendor process limits.

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 stated goal — verifying against published fab process limits 'to prevent CAM engineering query (EQ) rejections' — conveys the scenario that motivates using it. However, it never explicitly contrasts with the standards-based sibling audits (IPC-2221 clearance, IPC-6012 class), so an agent must infer which audit applies. Implied usage rather than explicit when/when-not guidance.

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