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

Annotations already fix the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false), and the description adds real behavioral context: the default learned router, what the 'ts' local router additionally does (keeps partial copper, last-chance welds, plane-island bridges), and the default time budget.

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 core behavior before the router and budget details. Mostly earns its length, though the clause about welds and plane-island bridges is comparatively dense for a subordinate default.

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 6-parameter mutating tool with no output schema, the description covers router choice and budget but omits pours semantics and says nothing about failure/partial-completion behavior beyond the wait_s schema note pointing at get_board_job.

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 only 50% (nets, wait_s, design_id documented). The description compensates partially by explaining the router enum values and the default budget, but pours is left undefined in both places and the nets parameter semantics are not elaborated on.

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 pair — keep the copper of already-connected nets and route the still-open nets — and explicitly identifies the sibling it derives from ('route_board with preserve_existing'), so an agent can tell it apart from route_board without opening either 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?

It gives a router-selection rule ('ts' for the local router, learned service by default) but never states when to reach for repair_board versus ripup_routing, finish_board, or plain route_board. Usage is implied by the mechanics rather than spelled out.

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