Validate FHIR R4/R5 resources and bundles against profiles (US Core, etc.) with precise, line-level error reporting.
Single tool 'fhirlint_scan' has a reasonable description (127 chars, within 10-1024 range) but critical schema and parameter documentation gaps. Input schema exists but parameter 'target' lacks type specification in the visible code, only a string description is present. No output schema is documented. The tool description does not explain error handling, prerequisites, or what 'precise, line-level error reporting' means in practice. No guidance on when to use this tool vs alternatives. The implementation calls scan(target) and to_json() but the actual return structure is not documented in the MCP server code.
Validate FHIR R4/R5 resources and bundles against profiles (US Core, etc.) with precise, line-level error reporting.. Returns JSON findings.
Output schema not documented. Tool returns JSON findings but structure (fields, types, nesting) is not specified in MCP server definition. LLM cannot plan downstream processing or extract specific fields.
Parameter 'target' lacks type and format constraints. Description says 'Path to FHIR resource or bundle' but does not specify: file vs directory, absolute vs relative, required file extensions, max path length, or error behavior if path does not exist.
Tool description does not explain error cases or recovery. What happens if the file is invalid FHIR? If the path does not exist? If validation fails? LLM has no guidance on next steps.
No documentation of what 'precise, line-level error reporting' returns. Are findings returned as JSON objects with id/severity/line/message fields? Is there a total count? Pagination? LLM must guess the response structure.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 46 | 2026-07-28+ | v2 |
Tool name 'fhirlint_scan' is domain-specific but does not clearly distinguish it from other validation tools. Description mentions 'US Core' profiles but does not explain when to use this vs a generic FHIR validator or other linting tools.