Docs: Update CallToolResult parsing in README #812
Merged
+130
−0
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
d413cd7 to
e896ce2
Compare
felixweinberger
added a commit
to functicons/mcp-python-sdk
that referenced
this pull request
Jul 17, 2025
Instead of inline parsing examples in basic client code, this commit adds a dedicated 'Parsing Tool Results' section under Advanced Usage that comprehensively documents: - The structure of CallToolResult (content, structuredContent, isError) - How to parse different content types (TextContent, ImageContent, EmbeddedResource, ResourceLink) - Structured output handling for tools with outputSchema - Proper error handling using the isError field This provides a cleaner, more comprehensive reference for developers working with tool results in MCP. Github-Issue: modelcontextprotocol#812
The example in README.md for parsing the result of `session.call_tool` has been updated to reflect the structure of `CallToolResult`. This change aligns the README example with the type definitions in `mcp/types.py`.
1f979a7 to
93d8496
Compare
- Add new section under Advanced Usage for parsing CallToolResult objects - Create comprehensive example showing all content types (text, structured, embedded resources, images, errors) - Move parsing documentation to a dedicated section instead of inline examples - Improve discoverability and clarity of tool result parsing patterns
The original author's inline parsing examples are now redundant since we have a dedicated 'Parsing Tool Results' section under Advanced Usage. This commit removes all the duplicated content, keeping the documentation clean and focused.
felixweinberger
approved these changes
Jul 17, 2025
There was a problem hiding this comment.
Thank you for this contribution!
I think adding some parsing examples like this to docs makes sense - but I don't think we should be modifying existing code snippets + duplicate it in multiple places.
I've instead created a new section part of Advanced Usage specifically for parsing tool results of different types as an example and pushed that to this PR.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The example in README.md for parsing the result of
session.call_toolhas been updated to reflect the structure ofCallToolResult.This change aligns the README example with the type definitions in
mcp/types.py.Motivation and Context
How Has This Been Tested?
Breaking Changes
Types of changes
Checklist
Additional context