gov-data-mcp

site-due-diligence-bundle

Screen site coordinates across 20 federal environmental layers and return one go/caution/no-go fatal-flaw verdict with a 0-100 score for due diligence.

Instructions

Environmental Due Diligence Bundle: 20-Layer Site Scorecard. Environmental due diligence at $0.10 per property - one row per site, not per layer. Lat/lon plus radius returns a go/caution/no-go fatal-flaw verdict and 0-100 score across 20 federal layers: EPA contamination, FEMA flood, NWI wetlands, ESA habitat, karst, landslide, levee, dams, CBRS, pipelines. CHOOSE THIS when you want one combined go / caution / no-go verdict for a coordinate across many unrelated layers. It is NOT an ASTM records review: its contamination layer reads RCRA and TRI through ECHO only and omits coordinate-less Superfund records. For a contamination-first question use epa-contaminated-site-screener. INPUTS: assets is required (lat/lon per site). radiusMiles sets the proximity layers only; point-in-polygon layers ignore it. maxAssets is the cost cap, one billed row per site, so start with 1-3 sites. Reads live from the official government source. Call describe-gov-data-tool (free) for a verified example input. COST AND SIDE EFFECTS: read-only with respect to the government source — it never writes to any external system — but each call starts a metered run on YOUR Apify account, billed $0.1 per result ($100 per 1,000). Lower on paid Apify plans, down to $30.00 per 1,000. Nothing is charged when a run fails. Store page: https://apify.com/malonestar/site-due-diligence-bundle

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "assets": "<assets>"
    },
    "name": "site-due-diligence-bundle"
  }
}

Input Schema

Name	Required	Description
`assets`	Yes	List of sites to run the full fatal-flaw scorecard on. Each item is an object with numeric lat and lon (WGS84 decimal degrees) and an optional label. One billable scorecard row is returned per successfully screened asset -- invalid coordinates are returned in a separate non-billable dataset. Example: [{"lat":29.7355,"lon":-95.2601,"label":"Houston Ship Channel parcel"}]. Example: [{"lat":29.7355,"lon":-95.2601,"label":"Houston Ship Channel industrial site, TX"},{"lat":44.29,"lon":-105.5,"label":"Gillette, WY greenfield (coal-country)"}].
`maxAssets`	No	Maximum number of assets to screen from the list (safety cap). Extra assets beyond this are ignored. Applied by default if omitted: 250.
`radiusMiles`	No	Search radius in statute miles for the proximity layers (EPA contamination, ESA critical habitat, transmission grid, wildfire flag, landslide nearby-search, CWA 303(d) impaired waters, tank/spill registries, gas pipelines, NWI wetlands, NRHP historic resources, and NID dams). Point-in-polygon-only layers (protected lands, flood/NRI county, seismic, IRA energy community, karst, USACE levee, CalFire FHSZ, NAAQS nonattainment, CBRS) ignore this. Accepts 0.25 to 25; smaller means a tighter on-site screen. Example: 1.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.2Aug 20, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Goes well beyond the annotations: it discloses that each call starts a metered run on the caller's Apify account at $0.10 per result, that billing is per site not per layer, that failures are not charged, and that reads come live from official government sources. It also reconciles the readOnlyHint=false annotation by clarifying the tool is read-only toward the government source but is not a free operation. Minor gap: run duration and async/polling behavior are not mentioned.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the value proposition, then selection guidance, then inputs, then cost and side effects — a logical order with labeled sections that scan well. It is dense but slightly over-long, with the price repeated three ways ($0.10/property, $100 per 1,000, $30 per 1,000 on paid plans) plus a store URL that duplicates the metadata.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-value burden and does so: one row per site, a go/caution/no-go verdict, and a 0-100 score, with invalid rows separated out. Combined with the cost model, layer list, and the free describe-gov-data-tool pointer for a verified example input, an agent has everything needed to call this correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, but the description adds real semantics: radiusMiles applies only to proximity layers while point-in-polygon layers ignore it, maxAssets is a billed cost cap of one row per site, and invalid coordinates land in a separate non-billable dataset. The only missed opportunity is not restating the accepted lat/lon format, which the schema already covers.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('one combined go / caution / no-go verdict for a coordinate across many unrelated layers') plus the concrete output shape (fatal-flaw verdict and 0-100 score over 20 federal layers). It explicitly distinguishes itself from the closest sibling by naming epa-contaminated-site-screener as the contamination-first alternative.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit 'CHOOSE THIS when...' condition, an explicit 'NOT an ASTM records review' exclusion with the reason (RCRA/TRI via ECHO only, omits coordinate-less Superfund records), and names the alternative to use for contamination-first questions. There is also a starting-scale recommendation ('start with 1-3 sites') tied to the cost cap.

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

Deploy Server