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

With destructiveHint already declaring the risk, the description adds substantial context: exactly which item classes are removed, the definition of a stub, that contact is copper overlap 'as KiCad judges it', that zones are refilled first, that locked items are preserved, and a rollback guarantee if unconnected count or DRC errors rise. This goes well beyond annotation coverage.

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 'Sweep the routing:' and each sentence earns its place by adding a distinct behavioral fact. It is dense and parenthetical, which slightly hurts readability, but there is no 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 destructive, output-schemaless tool, the description is nearly complete: it covers what is destroyed, the safety rollback, locked-item preservation, and part of the return (list_removed). It could say more about the overall response shape, but no critical calling information is missing.

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 low (25%), and the description compensates by explaining the flags semantically: trim_overhangs is named with its meaning, list_removed 'names every item that went', refill is tied to the zone refill, and the stub/dangling/via flags map to the described removal categories. It leaves some flags (dangling_tracks, duplicate_tracks, unconnected_vias) to inference but adds real value over the bare schema.

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?

States a specific verb (sweep) and precisely enumerates the resources it touches: zero-length tracks, duplicate tracks, stub tracks, and vias meeting their net on fewer than two layers. However, it never differentiates itself from close siblings like prune_vias, polish_vias, or tidy_copper, so the agent must infer which cleanup tool applies.

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 (a post-routing sweep that refills zones and guards on unconnected/DRC counts) rather than stated. There is no explicit 'use this when' or routing to an alternative such as prune_vias or tidy_copper, so the boundary between the several cleanup tools remains ambiguous.

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