pcb_delete_object

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

No annotations exist, so the description carries the full burden, and it does meaningful work: it defines the exact proximity metric per object type (track segment less half width, via centre less radius, bounding rectangle otherwise) and explains the 'others_as_close' tie-count in the return. Gaps remain for a destructive tool with no annotation coverage — it never says whether the delete is undoable, whether it requires a selection/lock state, or what the 'deleted status' is when no candidate is found.

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 with a one-sentence summary, then the matching semantics, then args, then returns — good ordering. It is somewhat long: the distance-metric paragraph is dense, and the Returns section restates what the output schema already declares, which is redundant given has_output_schema=true.

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 4-parameter destructive geometry operation with an output schema and no annotations, the definition covers selection semantics, parameter meanings, and the sibling alternative. The remaining gap is safety context — nothing about undo/reversibility or permission requirements for removing copper from a board.

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 description coverage is 0% (titles and types only), and the description fully compensates: units for x/y ('mils'), the meaning of layer and its default, and an explicit enumeration of all nine object_type values with a one-line gloss each. This is meaning the schema alone cannot convey.

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 opening line states a specific verb and resource plus the selection mechanism: 'Delete a PCB object closest to specific coordinates on a layer.' It is immediately distinguishable from siblings like obj_delete (bulk deletes) or pcb_unroute (net-based removal) because the selection model is proximity-based.

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 concrete operational precondition (nearest match within 100 mils) and points to the alternative for bulk/filter-based work: 'for bulk/filter-based deletes use obj_delete'. However, that routing hint is buried in a parenthetical inside the parameter list rather than stated up front, and there is no guidance on what to do when nothing is within 100 mils.

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