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

Annotations declare a non-read-only but non-destructive, closed-world mutation; the description adds the key behavioral fact that geometry is collision-checked against other nets, tracks, vias, and the board edge, so the agent knows this is an additive, obstacle-avoiding edit. It does not discuss reversibility (e.g., undoing via ripup_routing) or what happens on partial failure, leaving a small gap.

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 sentences, front-loaded with the action and its rationale, then safety, then workflow. The first sentence is long and clause-heavy but every clause carries information an agent needs; nothing is filler.

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 a 7-parameter, no-output-schema board mutation, the description covers purpose, safety constraint, and pipeline ordering, which is the bulk of what is needed. It leaves out any expectation about the returned report (e.g., how many ties were placed) and defers async job behavior entirely to the wait_s schema text.

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%, so defaults and bounds for nets, layers, max_mm, width_mm, avoid_copper, and wait_s are already documented. The description adds conceptual framing (what a 'tie' is and why it exists) but no syntax, unit, or format detail beyond the schema, so baseline 3 applies.

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?

States a precise verb and resource — tie neighbouring same-net SMD pads of plane nets together on their own layer with short tracks — and adds the design intent (one shared via per group instead of one per pad). This is clearly distinguishable from siblings like prune_vias, route_board, and fill_zones even though none are named as substitutes.

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 explicit pipeline placement: run before routing and then route with preserve_existing (the default), or run after routing/prune_vias and re-run prune_vias on those nets. It also states a hard precondition for placement — a tie is only placed where it misses every other net's pad, tracks, vias, and the board edge.

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