pcb_import_placement

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

With no annotations, the description carries the full burden and does real work: it discloses that only existing components are affected, that coordinates are absolute in mils and rotation in degrees, that `side`/`layer` flip the component, that `layer` overrides `side`, and that the return is `{"applied": N, "failed": M}`. It does not state atomicity, whether a partial failure leaves the board half-imported, or what happens when a designator does not resolve.

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?

Front-loaded one-line purpose, then scope/units, then a compact Args/Returns block. Every line carries information; nothing is repeated from structured fields or padded with 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?

For a single-parameter bulk-mutation tool with an output schema present, the description covers purpose, input shape, units, and result envelope — enough to call it correctly. The remaining omission is failure behavior (partial application, unknown designators), which matters for a mutation tool with no annotations to signal safety.

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 0% (the single `placements` array degrades to `additionalProperties: true`), so the description is the only documentation — and it fully enumerates the per-entry fields with required/optional status, units, and the side/layer precedence rule. The gap is defaults semantics: for optional `x`/`y`/`rotation`, it never says whether omission leaves the current value untouched or resets it, which is the ambiguity an agent is most likely to hit.

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?

Specific verb+resource ("Position components from a coordinate list") with the domain alias "pick-and-place import" so an agent can map a user's phrasing onto it. It also anchors to a known sibling by declaring itself the inverse of `pcb_export_coordinates`, which uniquely disambiguates it from `pcb_move_components`/`pcb_place_components`-style siblings.

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 inverse-of-export framing makes the intended scenario clear (bulk repositioning from an external coordinate file) and the constraint "component already on the board, by designator" tells the agent this is not a create path. It stops short of naming the alternative to use when components do not yet exist (e.g. `pcb_place_components`) or when ad-hoc moves are wanted.

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