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

With destructiveHint=true already declared, the description still adds real behavioral value: the keep-only-if-fewer-vias rule, the no-new-open-item/no-DRC-error gate, the island-bridging special case, and the honest non-determinism note on pours. It does not cover runtime/rate behavior or what happens on a partially applied run, so it is strong but not exhaustive.

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?

One dense paragraph that front-loads the workflow and keeps every clause earning its place; the parenthetical island note and the closing follow-up sentence are the only slightly crowded parts. Efficient despite covering a lot of ground.

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 14-param destructive mutation with a nested ml_options object and no output schema, the description supplies the essential workflow, safety gate, and follow-up calls. The gaps are limited to a handful of tuning parameters already documented in the schema.

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 79% with 14 params, so most semantics live in the schema. The description adds conceptual meaning for via_cost ('high via price') and bridge_islands (one via per island) but says nothing about nets, pairs, router, wait_s, or the budget parameters, so it only marginally exceeds baseline.

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?

Names a specific verb (polish), resource (vias), and scope (net by net, fewest vias first), and the description makes clear it is a rip-reroute-keep loop rather than a plain router or prune. An agent can distinguish it from route_board, prune_vias, and ripup_routing without opening a 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?

States the prerequisites explicitly (after route_board and prune_vias) and the follow-ups (run_drc, get_score), plus notes a second pass sometimes finds more. The ordering and when-to-run context are fully spelled out rather than inferred.

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