Merge branch 'main' into feat/tasks

Author: LucaButBoring

blog/content/posts/2025-11-03-using-server-instructions.md

@@ -38,7 +38,7 @@ It's like having a pile of notes on my garage workbench, each trying to explain
 
 Similarly, for global instructions that you want the LLM to follow, it's best to inject them into the model's system prompt instead of including them in multiple tool descriptions or standalone prompts.
 
-This is where **server instructions** come in. Server instructions give the server a way to inject information that the LLM should always read in order to understand how to use the server - independent of individual prompts, tools, or messages.
+This is where **server instructions** come in. [Server instructions](https://modelcontextprotocol.io/specification/draft/schema#initializeresult) give the server a way to inject information that the LLM should always read in order to understand how to use the server - independent of individual prompts, tools, or messages.
 
 ### A Note on Implementation Variability
 

docs/specification/draft/changelog.mdx

@@ -18,6 +18,7 @@ the previous revision, [2025-06-18](/specification/2025-06-18).
 
 1. Clarify that servers must respond with HTTP 403 Forbidden for invalid Origin headers in Streamable HTTP transport. (PR [#1439](https://github.com/modelcontextprotocol/modelcontextprotocol/pull/1439))
 2. Updated the [Security Best Practices guidance](https://modelcontextprotocol.io/specification/draft/basic/security_best_practices).
+3. Clarify that input validation errors should be returned as Tool Execution Errors rather than Protocol Errors to enable model self-correction ([SEP-1303](https://github.com/modelcontextprotocol/modelcontextprotocol/issues/1303)).
 
 ## Other schema changes
 

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

docs/style.css

@@ -168,7 +168,7 @@ body:has(#schema-reference) {
       font-family: var(--font-mono);
       font-weight: 700;
 
-      scroll-margin-top: 5rem;
+      scroll-margin-top: 8rem;
     }
 
     & > .tsd-comment,