Skip to main content
Glama

get_readwise_highlights_by_document_ids

Retrieve highlights from Readwise by specifying document IDs to access saved annotations and notes from specific documents.

Instructions

Get highlights from Readwise by document ids.

Args:
    document_ids (List[int]): The IDs of the documents to retrieve highlights for.

Returns:
    List[Highlight]: A list of Highlight objects containing the highlights from the specified document.

Raises:
    ValueError: If no document IDs are provided.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
document_idsYes

Implementation Reference

  • The primary handler function for the tool 'get_readwise_highlights_by_document_ids'. Decorated with @mcp.tool() for registration, it validates the document_ids input, concurrently calls the helper get_highlight_by_document_id for each ID, gathers results, flattens the list of highlights, and returns it.
    @mcp.tool()
    async def get_readwise_highlights_by_document_ids(
        document_ids: List[int],
    ) -> List[Highlight]:
        """
        Get highlights from Readwise by document ids.
    
        Args:
            document_ids (List[int]): The IDs of the documents to retrieve highlights for.
    
        Returns:
            List[Highlight]: A list of Highlight objects containing the highlights from the specified document.
    
        Raises:
            ValueError: If no document IDs are provided.
        """
    
        if not document_ids:
            raise ValueError("No document IDs provided")
    
        # Create a list of tasks (co-routines), one for each document ID
        tasks = [get_highlight_by_document_id(READWISE_API_KEY, doc_id) for doc_id in document_ids]
    
        # Execute all tasks concurrently and gather the results
        results = await asyncio.gather(*tasks)
    
        highlights: List[Highlight] = []
    
        # Flatten the list of lists into a single list of highlights
        for doc_highlights in results:
            highlights.extend(doc_highlights)
    
        return highlights
  • Pydantic BaseModel defining the Highlight type, which is used in the tool's return type List[Highlight]. This serves as the output schema.
    class Highlight(BaseModel):
        """Represents a highlight from Readwise API."""
    
        id: int
        text: str
        note: str
        location: int
        location_type: str
        highlighted_at: Optional[datetime] = None
        url: Optional[HttpUrl] = None
        color: str
        updated: datetime
        book_id: int
        tags: List[Tag] = []
  • Core helper function that retrieves all highlights for a single document ID from the Readwise API, including pagination logic using get_data.
    async def get_highlight_by_document_id(api_key: str, document_id: int) -> List[Highlight]:
        """Get highlights by document id."""
    
        url = f"{READWISE_API_URL}/highlights/"
        params = {"book_id": document_id, "page_size": 100}
    
        highlights: List[Highlight] = []
        first_request = True
        while True:
            # Pass params only on the first request.
            current_params = params if first_request else None
            hs = await get_data(api_key, url, current_params)
            first_request = False
    
            hs_results = hs["results"]
    
            highlights.extend([Highlight(**h) for h in hs_results])
    
            total_highlights = hs["count"]
            logging.info(f"Total highlights: {total_highlights}")
            url = hs.get("next", None)
    
            if not url:
                break
    
            await asyncio.sleep(DEFAULT_SLEEP_BETWEEN_REQUESTS_IN_SECONDS)
    
        return highlights
  • server.py:98-98 (registration)
    The @mcp.tool() decorator registers the get_readwise_highlights_by_document_ids function as an MCP tool.
    @mcp.tool()
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. While it mentions the return type and a potential error case (ValueError for empty input), it lacks critical information such as whether this is a read-only operation, rate limits, authentication requirements, pagination behavior, or what happens with invalid document IDs. The description is insufficient for a tool with no annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is efficiently structured with clear sections (Args, Returns, Raises) and uses minimal, purposeful sentences. Every element adds value: the opening statement defines the tool, and the structured sections provide essential documentation without redundancy or fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (1 parameter, no output schema, no annotations), the description covers the basics but has significant gaps. It explains the parameter and return type adequately but lacks behavioral context (e.g., read-only status, error handling beyond one case) and doesn't address sibling tool relationships. It's minimally viable but incomplete for optimal agent use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds meaningful context about the single parameter 'document_ids' by specifying it's 'The IDs of the documents to retrieve highlights for' and mentioning the ValueError case if none are provided. Since schema description coverage is 0%, this compensates well by explaining the parameter's purpose beyond the basic schema type definition.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with a specific verb ('Get highlights') and resource ('from Readwise by document ids'), making it immediately understandable. However, it doesn't explicitly differentiate from sibling tools like 'get_readwise_highlights_by_filters', which appears to serve a similar purpose with different filtering criteria.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'get_readwise_highlights_by_filters' or explain the trade-offs between filtering by document IDs versus other criteria, leaving the agent without contextual usage information.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/kiseki-technologies/kiseki-labs-readwise-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server