route_pair

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

Annotations only say readOnly=false, destructive=false; the description adds substantial behavioral context: the write gate ('Nothing is written if the plan has conflicts (copper of other nets, holes, keepouts, the partner trace) or dry_run=true; the plan is returned either way'), the skew-tuning bumps, and the layer change at a via. It does not cover rate limits or auth, but it goes well beyond the annotations.

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 purpose is front-loaded and each paragraph carries distinct information (centreline definition, side/crossing handling, explicit heads, chamfering, tuning, write gating). The prose is dense and occasionally run-on, but there is little filler to cut.

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 and a mutation tool, the description does the necessary work: it states the plan is always returned, what crossed=true means, and under what conditions nothing is written. It leaves the overall shape of the returned plan and several parameters implicit, but an agent has enough to invoke 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 0% across 16 parameters, so the description must carry the load. It meaningfully explains centreline_mm, p_head_mm/n_head_mm, the tail form with an embedded via, chamfer_mm, max_skew_mm, width/gap, and dry_run — roughly half the surface. tune, layer, p_net/n_net, and the via dimensions are left with no textual meaning beyond their names.

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+resource: 'Route a differential pair as two coupled traces along a centreline you choose.' This clearly distinguishes it from single-ended siblings like route_trace, route_net, and lay_bus without needing to open any schema.

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 clear operational context: the centreline runs from near start pads to near end pads, and p_head_mm/n_head_mm are for 'pins the automatic 45-degree fan-in cannot reach cleanly (e.g. through a gap in a pin row).' It also explains the crossed=true remedy. However, it never explicitly names an alternative tool (e.g. route_trace for single-ended nets), so routing between siblings remains implicit.

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