route_connection

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

With no annotations, the description carries the full burden and excels: it discloses the deterministic A* behavior, clearance resolution policy (max of explicit, DRC defaults, NetClass rules), the fact that results include clearance_rule_status and effective value (but not full DRC sign-off), the consistent use of millimeters regardless of document units, and the dry_run preview requirement. It also implicitly reveals mutation by stating 'previews without writing.'

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 description is a single, tightly packed paragraph without redundancy. Every sentence adds value: purpose, clearance semantics, output details, unit behavior, and the dry_run safeguard. It is front-loaded with the core action and front-outlined, achieving high information density with no 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?

Given the tool's complexity (22 parameters) and the existence of an output schema, the description provides essential behavioral context but leaves many parameters unexplained. It covers algorithm, clearance, units, and mutation workflow, but omits details on layer transitions, via behavior, and cost tuning. The output schema likely documents return values, but the parameter semantics gap prevents full completeness.

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%, so the description must explain parameters, but it only touches on clearance (omit or explicit) and dry_run/expected_sha256 workflow. Many critical parameters (net, start_object_id, end_object_id, layer, width, grid, path, txid, max_vias, via_cost, bend_cost, end_layer, max_nodes, via_style, max_detour, start_layer, time_budget_ms, preferred_layers, avoid_component_bodies) are not explained, leaving the agent to infer meaning solely from names and defaults.

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 clearly states the tool's function: 'Route one pad-to-pad connection with bounded deterministic 45-degree A*.' This specific verb+resource scope distinguishes it from siblings like route_net (multiple nets) or route_connections (batch), and the mention of the algorithm adds precision.

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 description provides workflow guidance, such as omitting clearance to use DRC rules, and the dry-run → expected_sha256 → commit sequence. However, it does not explicitly contrast with alternatives like route_connections or route_diff_pair, though the 'one pad-to-pad' phrasing implies the intended use case.

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