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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: vias are not layer-filtered, keepout areas are never removed, and locked items survive unless include_locked. It still doesn't state reversibility or whether the deletion can be undone, keeping it short of a 5.

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?

The text is dense and front-loaded, leading with the core action and then layering filter rules. Colon-and-parenthesis packing makes some sentences slow to parse, but essentially every clause carries information and nothing is 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 10-parameter destructive operation with no output schema and low schema coverage, the description covers the filter model, defaults, and protection rules (locked, keepouts) well. It omits what the call returns after deletion and any confirmation/undo expectations, which is a minor gap given annotations carry the destructive signal.

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 only 30%, so the description must carry the load, and it does: it explains the defaults for tracks/vias, the meaning of zones, that filters combine, that 'all' means unfiltered, and the region-matching rule for tracks versus zones. These are semantics the bare schema (booleans with no descriptions, a pattern-only layers array) does not supply.

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 opens with a specific verb and resource set: 'Delete tracks and vias' plus zones, with filter semantics spelled out. An agent immediately knows this is a destructive geometry-removal tool. It does not name or contrast any sibling (e.g. prune_vias, cleanup_board, tidy_copper), so it stays at 4 rather than 5.

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?

Usage is implied through filter semantics ('of the given nets, on the given layers, ... or all') and defaults ('tracks/vias ... both by default'), which lets an agent infer the rip-up-and-reroute workflow. However, there is no explicit when-to-use, when-not-to-use, or pointer to overlapping siblings like prune_vias or cleanup_board.

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