Skip to main content
Glama
ibm-ecm

Core Content Services MCP Server

Official
by ibm-ecm

get_searchable_property_descriptions

Get searchable property descriptions for a class. Provide the class symbolic name to retrieve only properties marked as searchable.

Instructions

Retrieves only the searchable properties of a class.

:param class_symbolic_name: The symbolic name of the class to retrieve searchable properties for

:returns: A list of CachePropertyDescription objects for properties that are searchable

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
class_symbolic_nameYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • The handler function for the 'get_searchable_property_descriptions' tool. It fetches class metadata via get_class_metadata_tool and filters the property_descriptions to return only those where is_searchable is True.
    async def get_searchable_property_descriptions(
        class_symbolic_name: str,
    ) -> Union[List[CachePropertyDescription], ToolError]:
        """
        Retrieves only the searchable properties of a class.
    
        :param class_symbolic_name: The symbolic name of the class to retrieve searchable properties for
    
        :returns: A list of CachePropertyDescription objects for properties that are searchable
        """
        class_metadata = await get_class_metadata_tool(
            graphql_client=graphql_client,
            class_symbolic_name=class_symbolic_name,
            metadata_cache=metadata_cache,
        )
    
        # If there was an error retrieving the class metadata, return it
        if isinstance(class_metadata, ToolError):
            return class_metadata
    
        # Filter the properties to include only searchable ones
        searchable_properties = [
            prop for prop in class_metadata.property_descriptions if prop.is_searchable
        ]
    
        # Return only the list of searchable property descriptions
        return searchable_properties
  • The tool is registered via the @mcp.tool decorator with name='get_searchable_property_descriptions' inside the register_search_tools function, which is called during server setup.
    def register_search_tools(
        mcp: FastMCP,
        graphql_client: GraphQLClient,
        metadata_cache: MetadataCache,
    ) -> None:
        @mcp.tool(
            name="get_searchable_property_descriptions",
        )
  • The CachePropertyDescription Pydantic model that defines the schema for the return type. It includes fields like symbolic_name, display_name, descriptive_text, data_type, cardinality, is_searchable, is_system_owned, is_hidden, and valid_search_operators.
    class CachePropertyDescription(BaseModel):
        """Describes detailed attributes or metadata about a property."""
    
        symbolic_name: str = Field(
            description="Symbolic name that is used to reference this property"
        )
        display_name: str = Field(description="A user displayable name for this property")
        descriptive_text: str = Field(
            description="Describes additional details about this property"
        )
        data_type: TypeID = Field(description="The type of data this property can hold")
        cardinality: Cardinality = Field(
            description="Whether this property holds a single value or multiple values."
        )
        is_searchable: bool = Field(
            description="Indicates whether searches can include conditions involving this property"
        )
        is_system_owned: bool = Field(
            default=False, description="Indicates whether this property is system-owned"
        )
        is_hidden: bool = Field(
            default=False, description="Indicates whether this property is hidden"
        )
        valid_search_operators: List[SearchOperator] = Field(
            description="The valid operators that can be used with this property in a search condition"
        )
Behavior2/5

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

No annotations; description only states it is a retrieval operation. Does not disclose any behavioral traits such as authorization, rate limits, or error handling.

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?

Concise docstring format; covers param and returns clearly. Could be more compact but is efficient.

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?

With one parameter and output schema present (not shown), description explains input and return type. Lacks differentiation from sibling and behavioral context, leaving minor gaps.

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?

Schema has 0% parameter descriptions, but the description provides a clear explanation of the 'class_symbolic_name' parameter, adding needed semantics.

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

Purpose5/5

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

Clearly states verb 'retrieves' and resource 'searchable properties of a class'. Distinguishes from sibling 'get_class_property_descriptions' by specifying 'only'.

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?

No guidance on when to use this tool vs alternatives like 'get_class_property_descriptions'. No exclusions or context provided.

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/ibm-ecm/cs-mcp-server'

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