[SEP-1303] Input validation errors as tool execution errors (modelcontextprotocol#1611)

* Merge invalid arguments and input data errors under a new input validation error category in tool execution errors

* Remove vague adverbes

Author: fredericbarthelet

docs/specification/draft/server/tools.mdx

@@ -396,14 +396,19 @@ Tools use two error reporting mechanisms:
 
 1. **Protocol Errors**: Standard JSON-RPC errors for issues like:
    - Unknown tools
-   - Invalid arguments
+   - Malformed requests (requests that fail to satisfy [CallToolRequest schema](specification/draft/schema#calltoolrequest))
    - Server errors
 
 2. **Tool Execution Errors**: Reported in tool results with `isError: true`:
    - API failures
-   - Invalid input data
+   - Input validation errors (e.g., date in wrong format, value out of range)
    - Business logic errors
 
+**Tool Execution Errors** contain actionable feedback that language models can use to self-correct and retry with adjusted parameters.
+**Protocol Errors** indicate issues with the request structure itself that models are less likely to be able to fix.
+Clients **SHOULD** provide tool execution errors to language models to enable self-correction.
+Clients **MAY** provide protocol errors to language models, though these are less likely to result in successful recovery.
+
 Example protocol error:
 
 ```json
@@ -417,7 +422,7 @@ Example protocol error:
 }
 ```
 
-Example tool execution error:
+Example tool execution error (input validation):
 
 ```json
 {
@@ -427,7 +432,7 @@ Example tool execution error:
     "content": [
       {
         "type": "text",
-        "text": "Failed to fetch weather data: API rate limit exceeded"
+        "text": "Invalid departure date: must be in the future. Current date is 08/08/2025."
       }
     ],
     "isError": true