MCP server providing tools for interacting with eco-mobility data, including station information, measurements, and historical data retrieval
Server has 5 tools with basic descriptions but critical gaps in schema documentation, parameter descriptions, and error handling. Tool names follow verb_noun convention (get_*, check_*) but parameter documentation is sparse. Input schemas are inferred from code rather than explicitly visible in registration. No output schemas documented. Error handling is minimal (generic McpResponse.Error calls). Descriptions are present but brief (10-50 chars), below the 50-200 char baseline for LLM optimization. Parameters lack type constraints and validation guidance.
Gets active stations.
Checks available stations.
Gets historical data for a specific station type, data type and time range.
Gets latest measurements for a specific station type and data type.
Gets stations informations based on station type and language.
Input schemas not explicitly visible in tool registration. Tool definitions use [McpTool] attributes with parameter names and types inferred from method signatures, but no explicit JSON Schema registration visible.
Parameter descriptions missing or minimal. Tools accept StationType, DataLanguage, DataType enums but no descriptions explain what values are valid, when to use each, or what the parameter controls. LLMs cannot infer enum values from names alone.
Tool descriptions are too brief (10-50 chars, below 50-200 char baseline). 'Gets stations informations based on station type and language' lacks context on when to call this vs other tools, what data is returned, and any prerequisites. Descriptions do not answer WHAT, WHEN, and WHAT-RETURNS.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 37 | <=2025-11-25 | v2 |
No output schema documented. Tools return CallToolResponse but no documentation of response structure, fields, or data types. LLMs cannot plan downstream calls or extract required data without knowing response shape.
Error handling is generic and non-actionable. Code shows McpResponse.Error(ex.Message) with no recovery guidance, error classification, or context. LLMs receive raw exception messages with no hint on whether to retry, ask user, or abort.