Build the board (sync to DRC)

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

Annotations declare destructiveHint=true, and the description usefully qualifies that risk by stating what is preserved: existing outline, existing tracks and placed parts are kept, with only new footprints placed and missing connections routed on a copper-bearing board. It also discloses the time-box behavior (default 45s, `pending`), which annotations cannot express. It stops short of stating whether a failed run leaves the board changed or how the `while_open`/`revert` path behaves.

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?

Content is front-loaded: the one-call scope and sibling replacement in the first two sentences, then conditional parameter semantics, then the `pending` continuation and a concrete example. Dense but every clause carries a distinct operational fact; nothing restates the schema verbatim.

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 15-parameter mutation tool with no output schema, the description covers the essentials: what the returned report contains (a line per stage, error groups with fixes, `fab_ready`, `next`) and what to do on `pending`. Minor gap is the absence of failure/reversion semantics for a destructive tool, and `destructiveHint=true` is never reconciled with the "existing parts are kept" reassurance.

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 already 93%, so the baseline is 3; the description earns above that by explaining conditional semantics the schema does not: width/height only apply with no outline or with outline='replace', and omitting both sizes the board from the parts. It does not add meaning for keep, moves, pour, router or layers, which remain schema-only.

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?

Opens with a specific verb-and-resource framing ("The whole board in ONE call") and enumerates the exact stages covered: schematic sync, outline, placement, routing, ground pour, DRC + ERC. It explicitly names the six sibling tools it replaces, so an agent can distinguish it from pcb_sync/pcb_route 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?

Gives an explicit routing rule ("Use it instead of pcb_sync, pcb_setup, pcb_place, pcb_route, pcb_pour and verify one after another") plus a condition for the parameters (width/height apply only when there is no outline, or with outline='replace'). It also tells the agent what to do on a partial result: "If the result has `pending` ... call board_build() again to continue."

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