Skip to main content
Glama
ibm-ecm

IBM Core Content Services MCP Server

Official
by ibm-ecm

document_search

Search for documents by content and metadata criteria. Use content-based retrieval and property filters to narrow results.

Instructions

PREREQUISITES IN ORDER: To use this tool, you MUST call two other tools first in a specific sequence.

  1. determine_class tool to get the class_name for search_class. The search class must be a document class or a document subclass.

  2. get_searchable_property_descriptions to get a list of valid property_name for search_properties

Description: This tool will execute a request to search for documents based on content and the metadata criteria.

:param search_term: The words for CBR search. This will be used to search for documents based on their CBR indexed content and metadata If empty string or None, then only search by metadata.

:param search_parameters (SearchParameters): provide parameters search_class and addiontal search conditions. Note the search_class is filled in by determine_class tool. search_properties inside search_parameters include any property being searched for and any search conditions. Note: additional properties beside the search_class are used to narrow down the result set, not to expand the result set, ie it does not make sense to support prompt such as: get me all XXXCBRDocClass documents that are created by XXXuser OR contains 'XXX Content' . For CBR, Content search will be carried out first to get a result set and additional properties are placed on this result set to narrow it down.

:returns: the released versions of documents that fit the search criteria. - if search by content and CBR is not enabled, tool will return a ToolError.

Example of search by content and class is CBR enabled: Prompt: get me all XXXCBRDocClass documents that are created by XXXuser and contains 'XXX Content' Request: { "doc_class": "XXXCBRDocClass", "max_results": 50, "search_parameters": { "search_class": "XXXCBRDocClass", "search_properties": [ { "operator": "=", "property_name": "Creator", "property_value": "XXXuser" } ] }, "search_term": "XXX Content" }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
search_parametersYesComplete set of parameters for executing a repository search.
search_termNo
max_resultsNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior4/5

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

Without annotations, the description discloses key behaviors: it returns released versions, performs content search first then narrows by properties, and returns a ToolError if CBR is disabled. It does not explicitly state it is read-only, but that is implied.

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 well-structured with clear sections (prerequisites, description, params, example). It is longer than necessary but each part serves a purpose. The prerequisites block is front-loaded, which is helpful.

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

Completeness5/5

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

Given the tool's complexity (nested parameters, CBR, required prerequisites) and the presence of an output schema, the description is complete. It covers prerequisites, usage, behavior, error handling, and includes an example, leaving little ambiguity for an AI agent.

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?

With only 33% schema coverage, the description adds significant value by explaining search_term's role (empty for metadata-only) and how search_parameters.prerequisites and narrowing logic work. The example further clarifies usage. However, the schema already has some descriptions for nested fields.

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 it searches for documents based on content and metadata criteria, specifying the scope (documents only) and mentioning CBR. However, it does not explicitly differentiate from sibling tools like repository_object_search, which may also search documents but without CBR.

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

Usage Guidelines4/5

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

The description provides explicit prerequisite steps (determine_class, get_searchable_property_descriptions) and explains when to use the tool (e.g., for content search, or metadata-only). It covers error cases (CBR not enabled) but does not directly state when not to use it (e.g., for non-document objects).

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/ibm-content-services-mcp-server'

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