Document result limits for MCP tools (#1395)

Closes SPLF-1441

<img width="1456" height="442" alt="CleanShot 2025-10-29 at 10 41 20"
src="https://github.com/user-attachments/assets/cbefe357-ee19-4dd5-a5c2-0ac0b3fb2db8"
/>

Author: janhartman

docs/api/mcp/index.mdx

@@ -5,7 +5,7 @@
 <TierCallout>
   Supported on [Enterprise](/pricing/enterprise) plans.
 </TierCallout>
-<Callout type="note">Available in version 6.8 and above</Callout>
+<Callout type="note">Available in version 6.8 and above.</Callout>
 <Callout type="note">This feature is [experimental](admin/beta_and_experimental_features#experimental-features) and might change or be removed in the future.</Callout>
 
 The Sourcegraph Model Context Protocol (MCP) Server provides AI agents and applications with programmatic access to your Sourcegraph instance's code search, navigation, and analysis capabilities through a standardized interface.
@@ -134,6 +134,10 @@ Locally-scoped servers take precedence over project-scoped servers with the same
 
 ## Available Tools
 
+<Callout type="info">
+All MCP tools implement result limits to ensure efficient operation and prevent context window overflow. These limits are designed to return the most relevant results while maintaining optimal performance. For large result sets, use pagination parameters (`after`/`before` cursors) where available, or refine your search with more specific filters.
+</Callout>
+
 The MCP server provides these tools for code exploration and analysis:
 
 ### File & Repository Operations
@@ -188,10 +192,6 @@ Perform exact keyword searches with boolean operators and filters.
 
 **Features:** Boolean AND/OR operators, regex patterns
 
-<Callout type="info">
-The `sg_keyword_search` MCP tool currently returns structured content wrapped in an extra content field. This mismatch can trigger validation errors in strict MCP clients, such as the Python MCP client. A fix is planned for a future release; for now, affected clients can manually unwrap the content field as a workaround.
-</Callout>
-
 #### `sg_nls_search`
 
 Semantic search with flexible linguistic matching.