Skip to main content
Glama

fetchDocuments

Retrieve documents from a knowledge base using filters for type, source, status, or metadata, with pagination and customizable property inclusion.

Instructions

Fetches documents from the namespace based on filter criteria. Supports pagination and including specific document properties.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
namespaceIdNo
documentIdsNo
paginationNo
tenantIdNo
filterConfigYes
includeConfigNo

Implementation Reference

  • Full tool registration and inline handler implementation for 'fetchDocuments'. Creates SourceSync client, processes parameters including enum conversions, and calls getDocuments API method wrapped in safeApiCall for error handling.
    server.tool(
      'fetchDocuments',
      'Fetches documents from the namespace based on filter criteria. Supports pagination and including specific document properties.',
      FetchDocumentsSchema.shape,
      async (params) => {
        return safeApiCall(async () => {
          const {
            namespaceId,
            tenantId,
            documentIds,
            pagination,
            filterConfig,
            includeConfig,
          } = params
    
          // Create a client with the provided parameters
          const client = createClient({ namespaceId, tenantId })
    
          // Add documentIds to filterConfig if provided
          if (documentIds && documentIds.length > 0 && !filterConfig.documentIds) {
            filterConfig.documentIds = documentIds
          }
    
          // Call the getDocuments method with properly structured parameters
          return await client.getDocuments({
            filterConfig: {
              ...filterConfig,
              // Convert string enum values to their SourceSync enum equivalents
              documentTypes: filterConfig.documentTypes?.map(
                (type: string) =>
                  SourceSyncDocumentType[
                    type as keyof typeof SourceSyncDocumentType
                  ],
              ),
              documentIngestionSources: filterConfig.documentIngestionSources?.map(
                (source: string) =>
                  SourceSyncIngestionSource[
                    source as keyof typeof SourceSyncIngestionSource
                  ],
              ),
              documentIngestionStatuses:
                filterConfig.documentIngestionStatuses?.map(
                  (status: string) =>
                    SourceSyncIngestionStatus[
                      status as keyof typeof SourceSyncIngestionStatus
                    ],
                ),
            },
            pagination,
            includeConfig: includeConfig || { documents: true },
          })
        })
      },
    )
  • Zod schema defining the input validation for the fetchDocuments tool, including optional namespaceId, documentIds, pagination, required tenantId, filterConfig, and optional includeConfig.
    export const FetchDocumentsSchema = z.object({
      namespaceId: namespaceIdSchema.optional(),
      documentIds: z.array(z.string()).optional(),
      pagination: PaginationSchema.optional(),
      tenantId: tenantIdSchema,
      filterConfig: FilterConfigSchema,
      includeConfig: z
        .object({
          documents: z.boolean().optional(),
          stats: z.boolean().optional(),
          statsBySource: z.boolean().optional(),
          statsByStatus: z.boolean().optional(),
          rawFileUrl: z.boolean().optional(),
          parsedTextFileUrl: z.boolean().optional(),
        })
        .optional(),
    })
  • Helper function used by all tools, including fetchDocuments, to safely execute API calls, format successful responses as MCP content, and handle errors appropriately.
    async function safeApiCall<T>(apiCall: () => Promise<T>) {
      try {
        const result = await apiCall()
        return {
          content: [
            {
              type: 'text' as const,
              text: JSON.stringify(result),
            },
          ],
        }
      } catch (error: any) {
        // Preserve the original error structure from SourceSync
        return {
          content: [
            {
              type: 'text' as const,
              text: JSON.stringify(error),
            },
          ],
          isError: true,
        }
      }
  • Helper function to instantiate the SourceSync client used in the fetchDocuments handler, falling back to environment variables.
    function createClient({
      apiKey,
      namespaceId,
      tenantId,
    }: {
      apiKey?: string
      namespaceId?: string
      tenantId?: string
    }) {
      return sourcesync({
        apiKey: apiKey || process.env.SOURCESYNC_API_KEY || '',
        namespaceId: namespaceId || process.env.SOURCESYNC_NAMESPACE_ID || '',
        tenantId: tenantId || process.env.SOURCESYNC_TENANT_ID || '',
      })
    }
Behavior2/5

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

With no annotations provided, the description carries full burden but offers minimal behavioral disclosure. It mentions pagination support and property inclusion but doesn't address permissions, rate limits, error conditions, or what happens when no documents match filters. For a read operation with complex filtering, this leaves significant gaps.

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 appropriately concise with two sentences that cover core functionality. It's front-loaded with the main purpose and follows with supporting features. No wasted words, though it could be more specific about what 'documents' refers to.

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?

For a complex tool with 6 parameters, 0% schema coverage, no output schema, and no annotations, the description is insufficient. It doesn't explain the relationship between parameters, what the tool returns, error handling, or usage constraints. The agent would struggle to use this effectively without trial and error.

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

Parameters2/5

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

With 0% schema description coverage and 6 parameters (including complex nested objects), the description provides almost no parameter guidance. It mentions 'filter criteria' and 'specific document properties' but doesn't explain what namespaceId, documentIds, pagination, tenantId, filterConfig, or includeConfig actually mean or how they interact.

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 ('Fetches documents') and resource ('from the namespace'), and mentions filter criteria, pagination, and property inclusion. It distinguishes itself from ingest/update/delete siblings but doesn't explicitly differentiate from search tools like semanticSearch or hybridSearch.

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 explicit guidance on when to use this tool versus alternatives. The description mentions filter criteria but doesn't specify when to use fetchDocuments versus search tools (semanticSearch, hybridSearch) or when filtering is required versus other document retrieval methods.

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/sitegpt/sourcesyncai-mcp'

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