Skip to main content
Glama

Search Documents

search_documents
Read-onlyIdempotent

Search Vault document metadata and summaries. When X1 has already selected the client and files for this conversation, use that selection without looking up another client. Otherwise, for a named client, pass their known authorized ID as clientId. If you do not know it, first use list_assigned_members with the client's name and use that person's returned id. If more than one person matches, ask which one instead of guessing. Without clientId or client context from X1, the search may use your own household or ask which client you mean; it does not select a client from the query. A member can search by the filename as shown in Vault even when the stored name uses separators. Title and tag metadata can appear before asynchronous body indexing is ready; use the body-content search tools for content and expect a just-saved document to report still indexing with an instruction to try again shortly. Each result includes a document id; an own-Vault result also includes an X1-authored documentUrl for a direct link. Use only that URL, never construct one from an id. On external professional connectors, use get_document_content or get_document_download_url once per document id when those tools are mounted. They require current download permission and household connected-document access, are rate limited, and record each release in household access history. Otherwise open the document in X1. Advisors and scoped specialists search explicitly shared documents plus active visible coordination-thread attachments, while managed-program roles search within their assignment scope.

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": {
      "query": "<query>"
    },
    "name": "search_documents"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYesSearch query
categoryNoFilter by category
clientIdNoAuthorized client or member ID. Keep any client and file selection supplied by X1. Otherwise, use a known authorized ID or the person's id returned by list_assigned_members. Without this ID or client context from X1, the search may use your own household or ask which client you mean; the query does not select a client.
dateFromNoFilter documents uploaded after this date (ISO 8601)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / clientId / description
      Previous value: -"Client or member user ID"New value: +"Authorized client or member ID. Keep any client and file selection supplied by X1. Otherwise, use a known authorized ID or the person's id returned by list_assigned_members. Without this ID or client context from X1, the search may use your own household or ask which client you mean; the query does not select a client."
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the read-only and idempotent annotations, the description discloses asynchronous body indexing, result fields including document id and X1-authored documentUrl, a warning never to construct URLs, and connector behavior involving permissions, rate limits, and access-history recording. These are substantive behavioral traits not covered by annotations.

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 long but front-loads the core purpose and then layers client selection, indexing, results, connectors, and role scoping in a logically structured way. It is dense rather than wasteful, though the final role-scoping sentence and repeated client-selection guidance make it heavier than ideal.

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?

For a complex search tool with no output schema, the description covers client scoping, body-indexing caveats, result fields, link handling, connector alternatives, permissions, rate limits, audit behavior, and role visibility. An agent has enough information to choose and invoke it correctly.

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 already 100%, so the baseline is 3. The description still adds practical meaning beyond the schema by clarifying that filename search works with the displayed name even when stored names use separators, and by emphasizing that the query does not select a client.

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?

The first sentence states a specific verb, resource, and scope: search Vault document metadata and summaries. It also distinguishes this from body-content search tools and from document-content retrieval tools, so an agent can identify the tool's role without opening the schema.

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

Usage Guidelines5/5

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

The description gives explicit routing: use X1's selected client/files when present; otherwise pass a known authorized clientId or use list_assigned_members. It also says what to do when multiple people match, what happens without clientId, when to use body-content tools instead, and when to use get_document_content or get_document_download_url.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.