pcb_cleanup_tracks

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

With no annotations, the description carries the full burden and does well: it discloses that slivers mode permanently deletes geometry below a threshold, and it spells out the exact preconditions under which merge fires (degree-2 junction, no via/pad/arc/third track) and claims it is 'safe to run on routed copper without breaking connectivity'. It stops short of stating undo/reversibility or whether an open board must be active.

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 summary, then a mode block, then args, then returns — a clean hierarchy. The trailing Args/Returns sections partially restate schema and output schema, which costs a little, but nothing is padded or vague.

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?

A destructive cleanup mutation with no annotations and only two loosely typed params is well covered: modes, thresholds, safety preconditions and the returned triple (slivers_deleted, merged, mode) are all explained. The remaining gap is operational context — permissions, whether a board must be focused, and undo behavior — which an agent would still want before calling a delete.

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%, so the description must compensate and does: the allowed values and default for mode ('slivers', 'merge', 'both', default 'slivers') and the meaning, unit and default of min_length_mils ('Sliver threshold (default 1)') are all stated, which is more than the bare schema types give.

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+resource+outcome ('Tidy stray track geometry: delete slivers and/or merge collinear runs') and immediately enumerates the two distinct operations. An agent can tell without opening the schema which of its many PCB siblings (pcb_delete_invalid_objects, pcb_trim_extend_track, pcb_normalize_vias) this one is not.

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?

Each mode is given a clear when-to-use condition: slivers 'catches the zero/near-zero stubs left behind by editing', merge applies to collinear same-layer/same-width/same-net pairs, and 'both' runs them in order. It never names a sibling tool or a when-not-to-use case (e.g. use pcb_delete_invalid_objects instead), so routing is implied rather than explicit.

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