Settlement layer for AI agent payments. Per-call billing, usage metering, and budget enforcement for MCP servers.
SettleGrid discovery server has 4 tools with minimal documentation. All tools have names starting with action verbs (search_, get_, list_), which is positive. However, tool descriptions are extremely brief (10-50 chars), parameter descriptions are missing entirely, and no input schemas are visible in the source code. The mcp.json file lists tool names and basic descriptions but provides no parameter type information, constraints, or output schemas. This is a discovery/metadata server, so the tools are simple, but the lack of schema documentation and parameter guidance makes it difficult for LLMs to use these tools correctly. No error handling guidance, no pagination info, and no output schema documentation visible.
Get information about a tool developer on SettleGrid
Get detailed information about a specific monetized AI tool
List all available tool categories on SettleGrid
Search monetized AI tools on SettleGrid by category and keywords
No input schemas visible in source code. Tools are registered in mcp.json with names and descriptions only; parameter types, constraints, and descriptions are completely absent.
Tool descriptions are extremely brief (10-50 characters). Current descriptions lack context for when/why to use each tool and what they return.
No parameter descriptions provided. 'query' and 'category' in search_tools, 'tool_id' in get_tool, and 'developer_id' in get_developer have no guidance on format, constraints, or expected values.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 41 | 2026-07-28+ | v2 |
No output schemas documented. LLMs cannot plan downstream calls or extract required fields (e.g., tool_id, developer_id) without knowing response structure.
No error handling guidance. No indication of what errors are retryable, what user-fixable errors look like, or how to recover from failures.