new feat: tool annotation
- Introduce
Tool annotations provide additional metadata about a toolβs behavior, helping clients understand how to present and manage tools. These annotations are hints that describe the nature and impact of a tool, but should not be relied upon for security decisions.
- Definition, default value and demo
demo
// A read-only search tool
{
name: "web_search",
description: "Search the web for information",
inputSchema: {
type: "object",
properties: {
query: { type: "string" }
},
required: ["query"]
},
annotations: {
title: "Web Search",
readOnlyHint: true,
openWorldHint: true
}
}
- detail: https://modelcontextprotocol.io/docs/concepts/tools#tool-annotations
Summary by CodeRabbit
- New Features
- Tools now include descriptive annotations, such as title and behavioral hints (e.g., read-only, destructive).
- Tests
- Updated tests to cover the new tool annotation fields.
Walkthrough
The changes introduce a new ToolAnnotation struct to encapsulate metadata about tools, including a title and four boolean behavioral hints. The Tool struct is extended with an Annotations field of this type. The NewTool constructor is updated to initialize this field with default values. A new functional option WithToolAnnotation() is added to set the annotations on a Tool instance. In the test suite, a Tool instance is updated to include specific annotation metadata. No other logic or control flow is modified.
Changes
| Files/Paths | Change Summary |
|---|---|
| mcp/tools.go | Added ToolAnnotation struct; extended Tool struct with Annotations field; updated NewTool constructor to initialize default annotations; added WithToolAnnotation() functional option. |
| server/server_test.go | Updated test to set the new Annotations field on a Tool instance with specific annotation metadata for testing. |
[!TIP]
β‘π¬ Agentic Chat (Pro Plan, General Availability)
- We're introducing multi-step agentic chat in review comments and issue comments, within and outside of PR's. This feature enhances review and issue discussions with the CodeRabbit agentic chat by enabling advanced interactions, including the ability to create pull requests directly from comments and add commits to existing pull requests.
π Recent review details
Configuration used: CodeRabbit UI Review profile: CHILL Plan: Pro
π₯ Commits
Reviewing files that changed from the base of the PR and between 12df8bae0ef85575a397380a3714a9b59d812afd and 67a5a263411f7f222220b08e3207b12e62b8efed.
π Files selected for processing (2)
mcp/tools.go(4 hunks)server/server_test.go(1 hunks)
β Files skipped from review due to trivial changes (1)
- server/server_test.go
π§ Files skipped from review as they are similar to previous changes (1)
- mcp/tools.go
πͺ§ Tips
Chat
There are 3 ways to chat with CodeRabbit:
- Review comments: Directly reply to a review comment made by CodeRabbit. Example:
I pushed a fix in commit <commit_id>, please review it.Generate unit testing code for this file.Open a follow-up GitHub issue for this discussion.
- Files and specific lines of code (under the "Files changed" tab): Tag
@coderabbitaiin a new review comment at the desired location with your query. Examples:@coderabbitai generate unit testing code for this file.@coderabbitai modularize this function.
- PR comments: Tag
@coderabbitaiin a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:@coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.@coderabbitai read src/utils.ts and generate unit testing code.@coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.@coderabbitai help me debug CodeRabbit configuration file.
Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.
CodeRabbit Commands (Invoked using PR comments)
@coderabbitai pauseto pause the reviews on a PR.@coderabbitai resumeto resume the paused reviews.@coderabbitai reviewto trigger an incremental review. This is useful when automatic reviews are disabled for the repository.@coderabbitai full reviewto do a full review from scratch and review all the files again.@coderabbitai summaryto regenerate the summary of the PR.@coderabbitai generate docstringsto generate docstrings for this PR.@coderabbitai resolveresolve all the CodeRabbit review comments.@coderabbitai configurationto show the current CodeRabbit configuration for the repository.@coderabbitai helpto get help.
Other keywords and placeholders
- Add
@coderabbitai ignoreanywhere in the PR description to prevent this PR from being reviewed. - Add
@coderabbitai summaryto generate the high-level summary at a specific location in the PR description. - Add
@coderabbitaianywhere in the PR title to generate the title automatically.
CodeRabbit Configuration File (.coderabbit.yaml)
- You can programmatically configure CodeRabbit by adding a
.coderabbit.yamlfile to the root of your repository. - Please see the configuration documentation for more information.
- If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation:
# yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json
Documentation and Community
- Visit our Documentation for detailed information on how to use CodeRabbit.
- Join our Discord Community to get help, request features, and share feedback.
- Follow us on X/Twitter for updates and announcements.
Hi @dugenkui03 @ezynda3 quick feedback. For me annotations aren't properly marshaled. I don't see them on the go client.
@StarpTech this will be fixed in #165