Skip to main content
Glama
Sign In

Connections

by icu.connections
OverviewDiscussionsAdmin

Search Google Drive

connections_storage_search_google_drive
Read-only

Search the connected Google Drive by file name or content, across My Drive, shared files and shared drives. Returns file ids, names, types, links and ownedByMe. query may be left out when owner or type is given. Up to 100 per page: pass nextPageToken back as page_token. Without a connected Drive, the answer is connected false plus a connect link.

Input Schema

NameRequiredDescriptionDefault
typeNoOnly this kind of file. document covers Google Docs, Word, PDF and text files.
limitNoMax files to return per page (default 10, maximum 100).
ownerNome: only files the member owns. shared: only files shared with them. any (default): both, plus shared drives.
queryNoText to look for in the file's name or its contents. Optional when owner or type is given.
personNoLinked person to run this call as (first name). Omit to run as the connection's holder.
projectNoWorkspace to run this call in (id or name).
page_tokenNoThe nextPageToken from the previous answer.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / page_token / description
      Previous value: -"The nextPageToken from a previous search_google_drive answer, to get the next page."New value: +"The nextPageToken from the previous answer."
    • addedInput schema / properties / person
      Added value: +{
+  "description": "Linked person to run this call as (first name). Omit to run as the connection's holder.",
+  "type": "string"
+}
  2. Changed1 schema field changed
    • addedInput schema / properties / project
      Added value: +{
+  "description": "Workspace to run this call in (id or name).",
+  "type": "string"
+}
  3. Added

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, non-destructive, open-world), so the bar is lower. The description still adds context the annotations cannot: the returned fields, the 100-per-page pagination contract with nextPageToken -> page_token, and the graceful 'connected false plus connect link' outcome when no Drive is linked.

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?

Four short sentences, front-loaded with purpose then scope, pagination, and failure mode. Dense with no filler, though the return-field sentence is somewhat list-like and the sentence order could tie pagination more tightly to the parameters.

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

Completeness4/5

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

With no output schema, the description compensates by naming returned fields and the unauthenticated response shape, and it covers pagination and the optional-query rule. What remains unstated is result ordering or relevance behavior, which matters for a search tool with a 100-item cap.

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 all seven parameters are already documented, including the owner and type enums. The description's only added meaning is the per-page cap and the dependency between query and owner/type, which is marginal; a 3 baseline is appropriate.

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?

It states a specific verb and resource ('Search the connected Google Drive') plus the searchable fields (file name or content) and the scope (My Drive, shared files, shared drives). It does not differentiate itself from the sibling connections_storage_list_files, so an agent must infer the search-vs-enumerate distinction.

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

Usage Guidelines3/5

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

The description gives one concrete usage rule: 'query may be left out when owner or type is given,' which tells the agent the minimum viable call. It never says when to use this rather than connections_storage_list_files or connections_storage_get_file, and names no exclusions.

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

All Connections toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources