Skip to main content
Glama
Core Content Services MCP Server

Core Content Services MCP Server

Official
by ibm-ecm

lookup_documents_by_path

Find documents by matching keywords at each folder path level, optionally within a specified document class; call determine_class first to get the class symbolic name.

Instructions

PREREQUISITE: To use this tool, you MUST call the determine_class tool first to get the class_symbolic_name. If the user does not specify a specific clas then call determine_class with the root Document class.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "keywords_at_path_levels": "<keywords_at_path_levels>"
    },
    "name": "lookup_documents_by_path"
  }
}

Input Schema

NameRequiredDescriptionDefault
class_symbolic_nameNoIf specified, a specific document class to look in for matching documents. The root Document class is used by default. Specify a class only if the user indicates that the documents should belong to a specific class.
keywords_at_path_levelsYesA list of lists of keywords to search for at each path level. The first dimension list is the number of path levels entered by the user. For each path level a sub list contains up to 3 words from the user's message for that level that might contain either the intermediate folder name or the actual document's containment name. Avoid using very common words such as "and", "or", "the", etc. for these keywords. Note that the matching of documents by path is based on the containment names of the documents filed in the folder, not the name of the documents themselves. The containment names of documents are usually the same or similar to the documents but they can be different in some scenarios.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.0.5
    • addedInput schema / properties / class_symbolic_name / description
      Added value: +"If specified, a specific document class to look in for matching documents.\nThe root Document class is used by default. Specify a class only if the user indicates\nthat the documents should belong to a specific class."
    • addedInput schema / properties / keywords_at_path_levels / description
      Added value: +"A list of lists of keywords to search for at each path level.\nThe first dimension list is the number of path\nlevels entered by the user. For each path level a sub list contains up to 3 words\nfrom the user's message for that level that might contain either the intermediate folder\nname or the actual document's containment name.\nAvoid using very common words such as \"and\", \"or\", \"the\", etc. for these keywords.\nNote that the matching of documents by path is based on the containment names of the documents\nfiled in the folder, not the name of the documents themselves.\nThe containment names of documents are usually the same or similar to the documents but\nthey can be different in some scenarios."
  2. Changed9 schema fields changedv1.0.4
    • addedInput schema / additionalProperties
      Added value: +false
    • removedInput schema / properties / class_symbolic_name / title
      Removed value: -"Class Symbolic Name"
    • removedInput schema / properties / keywords_at_path_levels / title
      Removed value: -"Keywords At Path Levels"
    • removedInput schema / title
      Removed value: -"lookup_documents_by_pathArguments"
    • removedOutput schema / $defs
      Removed value: -{
      -  "DocumentFilingMatch": {
      -    "description": "Information about a document where it is filed in a folder that matches a search.",
      -    "properties": {
      -      "containment_id": {
      -        "description": "The id of the containment relationship where the document is filed",
      -        "title": "Containment Id",
      -        "type": "string"
      -      },
      -      "containment_name": {
      -        "description": "The containment name of the document where filed in the folder",
      -        "title": "Containment Name",
      -        "type": "string"
      -      },
      -      "containment_path": {
      -        "description": "The containment path of the document where filed in the folder",
      -        "title": "Containment Path",
      -        "type": "string"
      -      },
      -      "document_class_name": {
      -        "default": "Document",
      -        "description": "Class identifier for the document that is filed",
      -        "title": "Document Class Name",
      -        "type": "string"
      -      },
      -      "document_id": {
      -        "description": "The id of the document that is filed in the folder",
      -        "title": "Document Id",
      -        "type": "string"
      -      },
      -      "document_name": {
      -        "description": "The name of the document that is filed in the folder",
      -        "title": "Document Name",
      -        "type": "string"
      -      },
      -      "folder_id": {
      -        "description": "The id of the folder where the document is filed",
      -        "title": "Folder Id",
      -        "type": "string"
      -      },
      -      "folder_name": {
      -        "description": "The name of the folder where the document is filed",
      -        "title": "Folder Name",
      -        "type": "string"
      -      },
      -      "folder_path": {
      -        "description": "The path of the folder where the document is filed",
      -        "title": "Folder Path",
      -        "type": "string"
      -      },
      -      "score": {
      -        "description": "The match score, higher values indicate better matches",
      -        "title": "Score",
      -        "type": "number"
      -      }
      -    },
      -    "required": [
      -      "containment_id",
      -      "containment_name",
      -      "containment_path",
      -      "document_id",
      -      "document_name",
      -      "folder_id",
      -      "folder_name",
      -      "folder_path",
      -      "score"
      -    ],
      -    "title": "DocumentFilingMatch",
      -    "type": "object"
      -  },
      -  "ToolError": {
      -    "description": "Represents an error response from a tool execution.\n\nThis class helps the LLM understand error messages and provides suggestions\nfor potential resolutions.",
      -    "properties": {
      -      "isError": {
      -        "const": true,
      -        "default": true,
      -        "description": "Indicates that an error occurred during tool execution if value is True",
      -        "title": "Iserror",
      -        "type": "boolean"
      -      },
      -      "message": {
      -        "description": "Detailed error message",
      -        "title": "Message",
      -        "type": "string"
      -      },
      -      "suggestions": {
      -        "description": "List of suggestions for resolving the error",
      -        "items": {
      -          "type": "string"
      -        },
      -        "title": "Suggestions",
      -        "type": "array"
      -      }
      -    },
      -    "required": [
      -      "message"
      -    ],
      -    "title": "ToolError",
      -    "type": "object"
      -  }
      -}
    • changedOutput schema / properties / result / anyOf
      Previous value: -[
      -  {
      -    "items": {
      -      "$ref": "#/$defs/DocumentFilingMatch"
      -    },
      -    "type": "array"
      -  },
      -  {
      -    "$ref": "#/$defs/ToolError"
      -  }
      -]New value: +[
      +  {
      +    "items": {
      +      "description": "Information about a document where it is filed in a folder that matches a search.",
      +      "properties": {
      +        "containment_id": {
      +          "description": "The id of the containment relationship where the document is filed",
      +          "type": "string"
      +        },
      +        "containment_name": {
      +          "description": "The containment name of the document where filed in the folder",
      +          "type": "string"
      +        },
      +        "containment_path": {
      +          "description": "The containment path of the document where filed in the folder",
      +          "type": "string"
      +        },
      +        "document_class_name": {
      +          "default": "Document",
      +          "description": "Class identifier for the document that is filed",
      +          "type": "string"
      +        },
      +        "document_id": {
      +          "description": "The id of the document that is filed in the folder",
      +          "type": "string"
      +        },
      +        "document_name": {
      +          "description": "The name of the document that is filed in the folder",
      +          "type": "string"
      +        },
      +        "folder_id": {
      +          "description": "The id of the folder where the document is filed",
      +          "type": "string"
      +        },
      +        "folder_name": {
      +          "description": "The name of the folder where the document is filed",
      +          "type": "string"
      +        },
      +        "folder_path": {
      +          "description": "The path of the folder where the document is filed",
      +          "type": "string"
      +        },
      +        "score": {
      +          "description": "The match score, higher values indicate better matches",
      +          "type": "number"
      +        }
      +      },
      +      "required": [
      +        "containment_id",
      +        "containment_name",
      +        "containment_path",
      +        "document_id",
      +        "document_name",
      +        "folder_id",
      +        "folder_name",
      +        "folder_path",
      +        "score"
      +      ],
      +      "type": "object"
      +    },
      +    "type": "array"
      +  },
      +  {
      +    "description": "Represents an error response from a tool execution.\n\nThis class helps the LLM understand error messages and provides suggestions\nfor potential resolutions.",
      +    "properties": {
      +      "isError": {
      +        "const": true,
      +        "default": true,
      +        "description": "Indicates that an error occurred during tool execution if value is True",
      +        "type": "boolean"
      +      },
      +      "message": {
      +        "description": "Detailed error message",
      +        "type": "string"
      +      },
      +      "suggestions": {
      +        "description": "List of suggestions for resolving the error",
      +        "items": {
      +          "type": "string"
      +        },
      +        "type": "array"
      +      }
      +    },
      +    "required": [
      +      "message"
      +    ],
      +    "type": "object"
      +  }
      +]
    • removedOutput schema / properties / result / title
      Removed value: -"Result"
    • removedOutput schema / title
      Removed value: -"lookup_documents_by_pathOutput"
    • addedOutput schema / x-fastmcp-wrap-result
      Added value: +true
  3. First observedv1.0.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations, the description carries the full burden. It explains the matching logic (by containment names) and parameter format but does not mention return behavior, errors, or side effects. Adequate but could be more transparent.

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

Conciseness3/5

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

The description is somewhat verbose, especially with the prerequisite emphasis. It is front-loaded with important info but could be more concise. Some repetition exists (e.g., calling determine_class explained twice).

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 presence of an output schema and full parameter coverage, the description covers prerequisites and matching logic. However, it lacks comparison with sibling tools (e.g., lookup_documents_by_name) and does not discuss edge cases or limitations. Adequate but not comprehensive.

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 coverage is 100%, and the description adds meaningful context beyond schema: explains the list-of-lists structure for keywords_at_path_levels, warns against common words, and clarifies class_symbolic_name usage. This adds value.

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

Purpose3/5

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

The description does not explicitly state the tool's purpose in a single sentence, but the title and context indicate it looks up documents by path. It lacks a clear verb+resource statement differentiating it from siblings like lookup_documents_by_name.

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 clearly states a prerequisite: must call determine_class first. It provides guidance on when to specify a class vs using root class. However, it does not directly contrast with sibling tools for alternative lookup methods.

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