Cloud cost summary MCP server for multiple vendors and months
Single tool with basic schema and description. Tool name 'get-cost' follows verb_noun pattern but description lacks depth on when/why to use it. Input schema present with Zod validation but parameters lack actionable constraints (no enums, ranges, or format guidance). Output is unstructured text rather than typed JSON. No error recovery guidance. Missing parameter descriptions for what vendors/months actually control in the response. No documentation of output structure, making downstream chaining impossible.
Get cloud cost summary for multiple vendors and months
Output is unstructured plain text instead of typed JSON object. LLM cannot extract structured data for downstream tool calls or parse cost breakdowns programmatically.
No output schema documented. Tool description does not specify what fields are returned (date, cost, accountId, productName, regionName). LLM cannot plan downstream operations or validate responses.
Parameter descriptions lack actionable constraints. 'vendors' and 'months' descriptions include examples ('AWS', 'Azure', '2024-04') but no enum, validation rules, or guidance on what happens if invalid values are passed.
Tool description (18 chars) is too brief. Does not explain WHEN to use this tool, what prerequisites exist (e.g., backend API must be running at localhost:8000), or what the response contains. Below 20-char threshold.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 54 | 2026-07-28+ | v2 |
No error handling or recovery guidance. If API at localhost:8000 is unreachable, tool returns 'Failed to load cost data' with no actionable next step for the LLM. No distinction between retryable vs fatal errors.