Skip to main content
Glama
zizzfizzix

Bing Webmaster Tools MCP Server

by zizzfizzix

get_deep_link_blocks

Retrieve blocked deep links for a website to identify and resolve URL indexing issues in Bing Webmaster Tools.

Instructions

Get deep link blocks for a site.

Args: site_url: The URL of the site

Returns: List[DeepLinkBlock]: List of deep link blocks

Raises: BingWebmasterError: If blocks cannot be retrieved

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
selfYes
site_urlYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • Registers the 'get_deep_link_blocks' tool using wrap_service_method, which decorates a wrapper function as an MCP tool (@mcp.tool()) and binds it to the 'get_deep_link_blocks' method on the 'links' service.
    get_deep_link_blocks = wrap_service_method(  # noqa: F841
        mcp, service, "links", "get_deep_link_blocks"
    )
  • Helper that creates the actual handler function for each tool: generates a wrapper with @mcp.tool(), copies signature/docstring from the service method, and executes the underlying service method via async with service as s: await getattr(getattr(s, service_attr), method_name)(*args, **kwargs). This is the core logic for all tools including get_deep_link_blocks.
    def wrap_service_method(
        mcp: FastMCP, service: BingWebmasterService, service_attr: str, method_name: str
    ) -> Callable[..., Any]:
        """Helper function to wrap a service method with mcp.tool() while preserving its signature and docstring.
    
        Args:
            mcp: The MCP server instance
            service: The BingWebmasterService instance
            service_attr: The service attribute name (e.g., 'sites', 'submission')
            method_name: The method name to wrap
    
        Returns:
            The wrapped method as an MCP tool
        """
        # Get the service class from our mapping
        service_class = SERVICE_CLASSES[service_attr]
        # Get the original method
        original_method = getattr(service_class, method_name)
        # Get the signature
        sig = inspect.signature(original_method)
        # Remove 'self' parameter from signature
        parameters = list(sig.parameters.values())[1:]  # Skip 'self'
    
        # Create new signature without 'self'
        new_sig = sig.replace(parameters=parameters)
    
        # Create wrapper function with same signature
        @mcp.tool()
        @wraps(original_method)
        async def wrapper(*args: Any, **kwargs: Any) -> Any:
            # Filter out any 'self' arguments that might be passed by the MCP client
            kwargs = {k: v for k, v in kwargs.items() if k != "self"}
    
            async with service as s:
                service_obj = getattr(s, service_attr)
                # Get the method from the instance
                method = getattr(service_obj, method_name)
                # Call the method directly - it's already bound to the instance
                return await method(*args, **kwargs)
    
        # Copy signature and docstring
        wrapper.__signature__ = new_sig  # type: ignore
        wrapper.__doc__ = original_method.__doc__
    
        return wrapper
  • In BingWebmasterService.__aenter__, instantiates the LinkAnalysisService as self.links, providing the underlying get_deep_link_blocks method implementation (from external bing_webmaster_tools library).
    self.links = link_analysis.LinkAnalysisService(self.client)
  • Maps 'links' service attribute to LinkAnalysisService class, used to fetch original method signature and docstring for the tool wrapper.
    "links": link_analysis.LinkAnalysisService,
  • Calls add_bing_webmaster_tools which includes the registration of get_deep_link_blocks and all other tools.
    add_bing_webmaster_tools(mcp, bing_service)
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. It mentions that it 'Raises: BingWebmasterError: If blocks cannot be retrieved', which adds some error-handling context. However, it fails to describe other key behaviors, such as whether this is a read-only operation, if it requires specific permissions, rate limits, or what happens in edge cases (e.g., invalid URLs).

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

Conciseness4/5

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

The description is structured with clear sections (Args, Returns, Raises) and is relatively concise, using only essential sentences. However, the inclusion of 'self' in the schema without explanation in the description suggests some inefficiency, as it could be more front-loaded with critical details.

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

Completeness4/5

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

Given the tool's moderate complexity (2 parameters, no annotations, but with an output schema), the description is reasonably complete. It covers the basic purpose, parameters, return type, and error handling. The presence of an output schema means it doesn't need to detail return values, but it could improve by explaining the 'self' parameter and providing more behavioral context.

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

Parameters3/5

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

The schema description coverage is 0%, so the schema provides no parameter details. The description adds minimal semantics by documenting 'site_url: The URL of the site' in the Args section, but it does not explain the 'self' parameter at all. This partial coverage compensates slightly but leaves one parameter undocumented, resulting in an average score.

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 action ('Get') and resource ('deep link blocks for a site'), making the purpose understandable. However, it does not differentiate this tool from sibling tools like 'get_deep_link' or 'get_deep_link_algo_urls', which might retrieve similar data, leaving some ambiguity about its specific scope.

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, such as sibling tools like 'get_deep_link' or 'get_deep_link_algo_urls'. It lacks context about prerequisites, exclusions, or typical use cases, offering only basic functional 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/zizzfizzix/mcp-server-bwt'

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