pcb_set_rule_properties

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

With no annotations to lean on, the description carries the full burden and does so unusually well: it discloses that writes are read back rather than assumed, that a non-Gap rule kind can silently retain its old gap, that Kind 63 is included on inference rather than a documented interface, and that properties_updated only counts verified writes. It also warns that assigning Priority crashes the DelphiScript engine, a concrete crash condition that is otherwise invisible.

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?

Purpose is front-loaded in the first sentence and the body is organized by RuleKind, which matches how an agent must reason about the 18 parameters. It is long and occasionally repeats itself (the gap read-back caveat is stated twice), but nearly every sentence carries non-obvious operational detail rather than restating the schema.

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 an 18-parameter mutation tool with no annotations and no schema descriptions, this is close to complete: it covers kind dispatch, unit traps, verification behavior, and the priority landmine. The one shortfall is the 'Returns' block, which lists only name, rule_kind, and properties_updated while the body additionally promises gap_written, gap_after_mm, via_sizes_mils, via_sizes_written, and via_note — an inconsistency the output schema may resolve but the description does not.

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%, so the description must compensate, and it does: it explains unit semantics, the gap_mils/gap_mm exclusivity and the precision trap (an integer mil field lands on 8 mils for a requested 0.2mm), the via-size set validation ordering (min <= preferred <= max, diameter > hole), and the bracket/&& requirement for scope query expressions. The only gap is gap_mm not appearing in the formal Args list despite being discussed in the body.

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?

Opens with a specific verb and resource: 'Update metadata AND constraint values of a named PCB design rule,' which immediately distinguishes it from read-side siblings like pcb_get_rule_properties and pcb_create_design_rule. It does not explicitly name or route away from pcb_set_rules_enabled, which also toggles a rule's enabled state, so the sibling differentiation is incomplete.

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?

Gives a clear operating contract — 'Pass only the parameters you want to change; everything else stays untouched' — plus a per-RuleKind table of which constraint fields apply to which rule kind, which is exactly the guidance an agent needs. It also routes the priority use case away from this tool to the Altium UI, though it never states when to use this tool versus pcb_set_rules_enabled or pcb_create_design_rule.

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