pbi-mcp exposes 4 tools with basic descriptions and parameter documentation via C# attributes. All tools have descriptions (10-100 chars) and input schemas with typed parameters. However, output schemas are completely undocumented, tools return plain strings with no structure guidance for LLMs. Parameter descriptions are minimal (10-20 chars) and lack format/constraint details. No error handling guidance, no pagination support for list operations, and no tool annotations (readOnlyHint, etc.). The server follows a simple verb_noun naming pattern (ListWorkspaces, ListDatasets, ListTables, ExecuteDax) but descriptions are generic and lack WHEN/WHY context. Composition is reasonable, tools chain naturally (list workspace → list datasets → list tables → execute DAX), but responses lack the IDs and metadata needed for efficient chaining.

• Document output schemas for all tools. E.g., ListWorkspaces should return {workspaces: [{id: string, name: string, description: string}], total: number}. Include field descriptions so LLMs know what to extract.
• Add pagination to list tools: add 'limit' (default 20, max 100) and 'offset' (default 0) parameters. Return total count and next_offset in response so agents can iterate large result sets.
• Expand parameter descriptions to 50-100 chars with format hints. E.g., 'The workspace (group) ID, a UUID returned by ListWorkspaces. Required to list datasets in that workspace.'
• Add error handling guidance in tool descriptions. E.g., 'If workspace not found, call ListWorkspaces() to verify the ID. If DAX query fails, check syntax and column names via ListTables().'
• Add readOnlyHint: true to all tool schemas to signal to LLMs that these are safe, non-destructive operations that can be retried without side effects.

Inferred effective spec: <=2025-11-25.

• Relies on Logging (deprecated) - log to stderr or use OpenTelemetry