Update to Water Investment Navigator

{
  "description": "Answer unit-cost questions for water and wastewater construction and supply — \"what does 12-inch PVC water main cost per foot\", \"is this bid price high\", \"typical price for a 36-inch gravity sewer\" — from awarded and bid unit prices, using the Water Investment Navigator MCP pricing tools.",
  "included_files": [],
  "name": "water-pricing-benchmarks",
  "skill_md_contents": "---\nname: water-pricing-benchmarks\ndescription: Answer unit-cost questions for water and wastewater construction and supply — \"what does 12-inch PVC water main cost per foot\", \"is this bid price high\", \"typical price for a 36-inch gravity sewer\" — from awarded and bid unit prices, using the Water Investment Navigator MCP pricing tools.\n---\n\n# Water pricing benchmarks\n\nUse the `water-investment-navigator` MCP tools `pricing_benchmarks` and `pricing_observations`.\n\n## Workflow\n\n1. `pricing_benchmarks(q=...)`: search by item words (size, material, item type),\n   e.g. `q=\"12 in PVC\"`. Each row is one canonical item **per unit** (`LF`, `EA`,\n   `CY`, `TON`, ...) with `observations`, `n_utilities`, `p25_unit_price`,\n   `median_unit_price`, `p75_unit_price` and `quality_tier`. Match the unit the\n   user asked about; the same item can appear once per unit.\n2. Check `quality_tier`:\n   - `benchmark`: enough observations across utilities to quote a range.\n   - `indicative`: quote it, but say it is indicative and give the count.\n   - `insufficient`: prices are null **by design**. Don't make up a number.\n     Say there isn't enough data, and optionally list the individual observations.\n3. `pricing_observations(canonical_item_id, unit=...)` shows the individual\n   prices behind a benchmark: utility, date, bidder, `price_kind`\n   (`awarded` vs bid/quoted), `is_winner`, quantity, and the `decision_id` to cite.\n   Use it to explain spread (small quantities cost more per unit; older\n   observations predate recent inflation) and to find comparable local prices.\n\n## Answering\n\n- Quote the median with the p25–p75 range, the unit, the observation count and\n  the date range (`first_observed`–`last_observed`).\n- Prefer awarded (winning) prices when the user asks what work \"costs\"; losing\n  bids are useful for spread, not for what utilities actually pay.\n- Prices are nominal and not adjusted for inflation or region. Say so when the\n  observation window spans several years.\n- Cite at least one source decision (`get_decision_source_text`) when a user\n  will act on the number.\n"
}