San Joaquin County, California open geospatial data (ArcGIS) — search datasets, query Feature Service layers, and retrieve layer schemas.
Three well-named, read-only tools with clear descriptions and complete input schemas. All tools follow verb_noun naming (search_*, query_*, layer_info). Descriptions are concise (100 - 200 chars) and explain purpose and usage. Input schemas include types and required fields. However, output schemas are not documented, LLMs cannot predict response structure for downstream planning. Parameter descriptions are good but lack explicit constraints (e.g., 'limit 1 - 50' is stated in description but not as JSON Schema minItems/maxItems). No error handling guidance or recovery paths documented. SSRF guard in layerUrl() is a security plus, but not exposed in tool descriptions.
Get an ArcGIS Feature/Map Service layer's schema by url: fields (name + type), geometry type, total record count, and capabilities.
Query an ArcGIS Feature Service / Map Service layer by its url (from search_datasets). SQL-like `where`, comma-separated `out_fields`, `order_by`, `limit`, `offset`. Returns attribute rows (and geometry). Use where="1=1" + out_fields="*" to sample.
Search San Joaquin County GIS open geospatial datasets (parcels, addresses, zoning & public works) by keyword. Returns each dataset's name, summary, record_count, owner/org, and its Feature Service `url` — pass that url to query_layer / layer_info.
Output schemas not documented. LLMs cannot predict response structure (fields, types, pagination) for downstream tool calls or data extraction.
No error handling guidance. Errors like 'ArcGIS Hub: 404' or 'url must be https' do not tell the LLM what to do next (retry, ask user, try alternative).
Parameter constraints (limit ranges, field formats) stated in descriptions but not enforced in JSON Schema (no minItems, maxItems, pattern, enum). LLMs may ignore text constraints.
query_layer accepts free-form SQL 'where' clause without validation or injection guards visible in tool description. LLM could pass malicious SQL.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 61 | 2026-07-28+ | v2 |
No pagination guidance in search_datasets description. LLM may not know how to iterate through large result sets or that limit caps at 50.