route_remaining

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

Goes well beyond the annotations by disclosing rip-up semantics (only traces laid in this run are ever ripped; existing routing stays), the 45-degree style, connector pin-field avoidance, a cost model (running through other nets' pours costs extra, a via is usually cheaper), and the dry_run default behavior with its one-undo-step write semantics and correctness checks.

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 scope and dry_run semantics are front-loaded and nearly every clause carries information, but the description is a dense run-on paragraph that mixes workflow positioning, geometry rules, cost heuristics and write semantics without structural breaks. Slightly long, though justified by the tool's complexity.

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 complex autorouting tool with no output schema and only generic annotations, this covers the workflow position, safety model (dry_run), rip-up boundary, geometry constraints and cost heuristics an agent needs to invoke it correctly. Only the unexplained parameters keep it from being airtight.

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?

With 0% schema coverage the description must carry all six parameters, and it only partially does: it defines widths as {net regex: mm}, explains include_pour_nets and dry_run thoroughly. It leaves 'nets', 'width_mm' (the 0.25 default) and 'allow_vias' undefined, so the agent is still guessing on half the inputs.

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 specific verb and resource ('route every connection still unrouted, shortest first') and defines its scope precisely as the leftover pass after pours, GND vias, close hops, fan-outs and bus lanes. An agent can tell it apart from the more targeted siblings like route_net, route_trace and route_pair by the 'remaining / still unrouted' scope alone.

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?

Explicitly situates the tool in a workflow ('the free-router step, after pours, GND vias, close hops, fan-outs and bus lanes') and gives an exclusion rule for pour nets unless include_pour_nets is set. It stops short of naming which sibling to prefer when you want a single trace or net, but the sequencing context is strong.

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