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

Annotations already declare the mutation profile (readOnlyHint=false, destructiveHint=false), and the description adds a genuinely useful behavioral promise: existing copper for already-connected nets is preserved. Beyond that it is silent on what happens to nets that cannot be routed, whether changes are reversible, or that the job may need polling.

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?

Two compact clauses with the core behavior front-loaded and no filler. The route_board-with-preserve_existing framing is efficient, though the trailing 'with the learned router service' phrase adds little for an agent.

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?

No output schema exists, so the description carries the return-behavior burden, and it partially does by noting the default budget and long-running nature of the operation. That is adequate for a six-parameter repair tool, though it never says how an agent learns which nets remain open after the run.

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 67%, and the description contributes a default execution budget of 120 s, which the time_budget_s parameter does not document. It says nothing about nets, pours, or compact beyond what the schema already provides, so the baseline 3 fits.

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 states a specific action: preserve the copper of already-connected nets and route only the still-open ones, which is precisely 'route_board with preserve_existing'. That clearly separates it from plain route_board. It stops short of a 5 because 'the learned router service' is unexplained jargon and the net-selection scope is only implied.

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?

Usage is implied by the verbs 'keep' vs 'route the nets still open', so an agent can infer this is the repair path after routing. But there is no explicit when-to-use guidance: nothing says to run diagnose_open_nets first, nor when to prefer ripup_routing or a fresh route_board instead.

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