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

Annotations declare destructiveHint=true, and the description richly earns that by explaining what actually happens: both legs are ripped and routed alone, and the new copper is kept only if four conditions hold (gain >= min_gain_pct, skew within max_skew_mm, no new open items or DRC errors, no more than max_extra_vias added). It also explains the mechanism/rationale ('pairs routed with the whole board lose their lanes').

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 single dense paragraph is front-loaded with the precondition 'After route_board' and every clause carries a distinct fact (mechanism, acceptance criteria, rationale, companion tool). It is information-dense rather than bloated, though the long chained sentence could be split for readability.

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 12-parameter mutation tool with no output schema, the description covers purpose, ordering, and the keep/reject criteria well enough to call it safely. It omits any mention of the returned job status/wait behavior (partially covered by the wait_s schema) and what happens when no pair meets the bar.

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 already 83%, but the description goes further by weaving min_gain_pct, max_skew_mm, max_extra_vias, and target_pct into a single acceptance-criteria narrative, clarifying how they interact rather than restating each. It adds real meaning, though undocumented params like bridge_islands and ml_options go unexplained.

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 states a precise verb+resource (re-route weakly coupled differential pairs one at a time) and a scoping rule (least coupled first), immediately distinguishing it from siblings like route_board, ripup_routing, and check_net_rules. An agent can tell what this does without inspecting the schema.

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 opening 'After route_board' gives an explicit ordering precondition, and 'Run check_net_rules before and after' names adjacent tools. It stops short of stating when NOT to run it (e.g. before routing or on non-diff nets), so it is clear context rather than full exclusion guidance.

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