Skip to main content
Glama

Import Library links

import_library_content
Idempotent

A local file uses create_library_upload_session, even without an attachment. Do not ask them to attach it in the chat. Import public Google Drive MP4/PDF file links as flat Library drafts. Pass individual file links; never pass a folder URL. Processing continues in the background. Poll get_library_upload_status until each item is ready, unavailable, or failed, then inspect or open it. For MP4s, ask the user: “Would you like to upload your videos as they are, or create new versions with Trainn AI? If you would like Trainn AI to create them, how should the videos turn out?” Wait for the answer unless the user already supplied their choice and instructions. A request describing the desired result chooses agentic_enhance; pass it as input_prompt. Collect instructions if missing. One prompt applies to every video; accept freeform instructions even if some edits are unsupported. Upload original uses preserve_original without input_prompt. Do not ask for PDFs. Publish only on request. Each result identifies its zero-based source_index. Keep accepted handles; retry only failed sources.

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": {
      "idempotency_key": "<idempotency_key>",
      "sources": "<sources>",
      "video_processing": "<video_processing>"
    },
    "name": "import_library_content"
  }
}

Input Schema

NameRequiredDescriptionDefault
sourcesYes
languageNoSupported narration language code, e.g. es for Spanish. Omit for the default.
input_promptNoOptional instructions for how Trainn AI should edit the video.
idempotency_keyYes
video_processingYesRequired user choice for every MP4 in this import. preserve_original keeps the source exact. agentic_enhance has Trainn AI rebuild it as a narrated walkthrough and uses the workspace's Trainn AI video usage. A silent source is acceptable for enhancement.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.5/5.0
Behavior4/5

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

Annotations declare non-read-only, open-world, idempotent, non-destructive, but the description adds much more: processing is asynchronous and requires polling get_library_upload_status, results carry a zero-based source_index, accepted handles should be kept and only failed sources retried, and publishing does not happen implicitly. It does not state permissions or rate/limit behavior, but coverage is strong for a write tool.

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?

Every sentence carries operational information, but the front-loading is poor: the actual purpose ('Import public Google Drive MP4/PDF file links as flat Library drafts') appears only after two sentences about a sibling tool, and the local-file/attachment instruction is worded ambiguously. The density of imperatives makes it hard to scan for the core action.

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 5-parameter async mutation tool with no output schema, the description covers the full lifecycle: submission constraints, background processing, polling, per-item result indexing, retention and retry policy, and publish gating. An agent can drive the tool end to end without further context.

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 60%, and the description compensates by explaining that video_processing is a required user choice with the semantic split between preserve_original and agentic_enhance, and that input_prompt carries the single set of instructions applied to every video in the batch. It does not explain idempotency_key or the sources[].title field, leaving a partial gap.

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?

States a specific verb and resource with scope: import public Google Drive MP4/PDF links as flat Library drafts, and explicitly contrasts with create_library_upload_session for local files. The distinction between file links and folder URLs further pins down the operation.

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?

Names the alternative (create_library_upload_session for local files), the prohibition (never pass a folder URL), the follow-up flow (poll get_library_upload_status), and the publishing condition (publish only on request). It also specifies when to stop and ask the user vs. proceed, including the exact branching question for MP4s.

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.

Resources