Skip to main content
Glama

roam_search_hierarchy

Search up or down the block hierarchy to find parent or child blocks. Specify a block UID to navigate its relational tree within a page or graph.

Instructions

Search for parent or child blocks in the block hierarchy. Can search up or down the hierarchy from a given block.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
parent_uidNoOptional: UID of the block to find children of
child_uidNoOptional: UID of the block to find parents of
page_title_uidNoOptional: Title or UID of the page to search in (UID is preferred for accuracy).
max_depthNoOptional: How many levels deep to search (default: 1)
graphNoTarget graph key from ROAM_GRAPHS config. Defaults to ROAM_DEFAULT_GRAPH. Only needed in multi-graph mode.
write_keyNoWrite confirmation key. Required for write operations on non-default graphs when write_key is configured.

Implementation Reference

  • Core handler executing the hierarchy search logic. Uses Datomic Datalog queries with an ancestor rule to find descendants (given parent_uid) or ancestors (given child_uid) of a block. Optionally scoped to a page via page_title_uid. Returns matched blocks with resolved content and depth information.
    export class HierarchySearchHandler extends BaseSearchHandler {
      constructor(
        graph: Graph,
        private params: HierarchySearchParams
      ) {
        super(graph);
      }
    
      async execute(): Promise<SearchResult> {
        const { parent_uid, child_uid, page_title_uid, max_depth = 1 } = this.params;
    
        if (!parent_uid && !child_uid) {
          return {
            success: false,
            matches: [],
            message: 'Either parent_uid or child_uid must be provided'
          };
        }
    
        // Get target page UID if provided
        let targetPageUid: string | undefined;
        if (page_title_uid) {
          targetPageUid = await SearchUtils.findPageByTitleOrUid(this.graph, page_title_uid);
        }
    
        let queryStr: string;
        let queryParams: any[];
    
        if (parent_uid) {
          // Search for all descendants using ancestor rule
          if (targetPageUid) {
            queryStr = `[:find ?block-uid ?block-str ?depth
                        :in $ % ?parent-uid ?page-uid
                        :where [?p :block/uid ?page-uid]
                               [?parent :block/uid ?parent-uid]
                               (ancestor ?b ?parent)
                               [?b :block/string ?block-str]
                               [?b :block/uid ?block-uid]
                               [?b :block/page ?p]
                               [(get-else $ ?b :block/path-length 1) ?depth]]`;
            queryParams = [ANCESTOR_RULE, parent_uid, targetPageUid];
          } else {
            queryStr = `[:find ?block-uid ?block-str ?page-title ?depth
                        :in $ % ?parent-uid
                        :where [?parent :block/uid ?parent-uid]
                               (ancestor ?b ?parent)
                               [?b :block/string ?block-str]
                               [?b :block/uid ?block-uid]
                               [?b :block/page ?p]
                               [?p :node/title ?page-title]
                               [(get-else $ ?b :block/path-length 1) ?depth]]`;
            queryParams = [ANCESTOR_RULE, parent_uid];
          }
        } else {
          // Search for ancestors using the same rule
          if (targetPageUid) {
            queryStr = `[:find ?block-uid ?block-str ?depth
                        :in $ % ?child-uid ?page-uid
                        :where [?p :block/uid ?page-uid]
                               [?child :block/uid ?child-uid]
                               (ancestor ?child ?b)
                               [?b :block/string ?block-str]
                               [?b :block/uid ?block-uid]
                               [?b :block/page ?p]
                               [(get-else $ ?b :block/path-length 1) ?depth]]`;
            queryParams = [ANCESTOR_RULE, child_uid, targetPageUid];
          } else {
            queryStr = `[:find ?block-uid ?block-str ?page-title ?depth
                        :in $ % ?child-uid
                        :where [?child :block/uid ?child-uid]
                               (ancestor ?child ?b)
                               [?b :block/string ?block-str]
                               [?b :block/uid ?block-uid]
                               [?b :block/page ?p]
                               [?p :node/title ?page-title]
                               [(get-else $ ?b :block/path-length 1) ?depth]]`;
            queryParams = [ANCESTOR_RULE, child_uid];
          }
        }
    
        const rawResults = await q(this.graph, queryStr, queryParams) as [string, string, string?, number?][];
        
        // Resolve block references and format results to include depth information
        const matches = await Promise.all(rawResults.map(async ([uid, content, pageTitle, depth]) => {
          const resolvedContent = await resolveRefs(this.graph, content);
          return {
            block_uid: uid,
            content: resolvedContent,
            depth: depth || 1,
            ...(pageTitle && { page_title: pageTitle })
          };
        }));
    
        const searchDescription = parent_uid
          ? `descendants of block ${parent_uid}`
          : `ancestors of block ${child_uid}`;
    
        return {
          success: true,
          matches,
          message: `Found ${matches.length} block(s) as ${searchDescription}`
        };
      }
    }
  • TypeScript interface defining the input parameters for the hierarchy search operation.
    export interface HierarchySearchParams {
      parent_uid?: string;  // Search for children of this block
      child_uid?: string;   // Search for parents of this block
      page_title_uid?: string;
      max_depth?: number;   // How many levels deep to search (default: 1)
    }
  • MCP tool schema definition for roam_search_hierarchy. Defines the input JSON Schema with parameters parent_uid, child_uid, page_title_uid, and max_depth.
    roam_search_hierarchy: {
      name: 'roam_search_hierarchy',
      description: 'Search for parent or child blocks in the block hierarchy. Can search up or down the hierarchy from a given block.',
      inputSchema: {
        type: 'object',
        properties: withMultiGraphParams({
          parent_uid: {
            type: 'string',
            description: 'Optional: UID of the block to find children of'
          },
          child_uid: {
            type: 'string',
            description: 'Optional: UID of the block to find parents of'
          },
          page_title_uid: {
            type: 'string',
            description: 'Optional: Title or UID of the page to search in (UID is preferred for accuracy).'
          },
          max_depth: {
            type: 'integer',
            description: 'Optional: How many levels deep to search (default: 1)',
            minimum: 1,
            maximum: 10
          }
        })
        // Note: Validation for either parent_uid or child_uid is handled in the server code
      }
    },
  • MCP server registration: case branch in the call-tool request handler that dispatches to toolHandlers.searchHierarchy(). Validates that exactly one of parent_uid or child_uid is provided.
    case 'roam_search_hierarchy': {
      const params = cleanedArgs as {
        parent_uid?: string;
        child_uid?: string;
        page_title_uid?: string;
        max_depth?: number;
      };
    
      // Validate that either parent_uid or child_uid is provided, but not both
      if ((!params.parent_uid && !params.child_uid) || (params.parent_uid && params.child_uid)) {
        throw new McpError(
          ErrorCode.InvalidRequest,
          'Either parent_uid or child_uid must be provided, but not both'
        );
      }
    
      const result = await toolHandlers.searchHierarchy(params);
      return {
        content: [{ type: 'text', text: JSON.stringify(result, null, 2) }],
      };
    }
  • ToolHandlers class delegates searchHierarchy to the searchOps (SearchOperations) instance.
    async searchHierarchy(params: {
      parent_uid?: string;
      child_uid?: string;
      page_title_uid?: string;
      max_depth?: number;
    }) {
      return this.searchOps.searchHierarchy(params);
    }
Behavior2/5

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

With no annotations, the description carries full burden. It implies a read-only search but does not disclose side effects, authentication needs, or return behavior. The presence of a write_key parameter is not explained in context of this search tool, potentially confusing.

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?

Two sentences, no redundant information. Every word carries meaning. Ideal conciseness for a simple search tool.

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

Completeness2/5

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

No output schema, so description should explain return format. It does not mention what is returned (blocks, UIDs, etc.) or any pagination/limitations. For a tool with 6 parameters, more context is needed.

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?

Schema coverage is 100%, so parameters are well-described in the schema. The description adds minimal value, only echoing the direction concept. Baseline 3 is appropriate as the description does not significantly enhance parameter understanding beyond the schema.

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 parent or child blocks in the block hierarchy, specifying direction up or down. It distinguishes from sibling tools by focusing on hierarchy, though it could be more explicit about the starting block.

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 versus alternatives like roam_search_block_refs or roam_search_by_text. It does not specify prerequisites or exclusions, leaving the agent to infer usage from the description alone.

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/2b3pro/roam-research-mcp'

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