Skip to main content
Glama
DatalisHQ

ZuckerBot

by DatalisHQ
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

zuckerbot_upload_ad_asset

Upload a NEW image or video file into the connected Meta ad account's library from a publicly reachable https URL or an absolute local file_path (local stdio/CLI only).

Instructions

Upload a NEW image or video file into the connected Meta ad account's library from a publicly reachable https URL or an absolute local file_path (local stdio/CLI only). Choose exactly one of asset_url, file_path, or files (a batch of up to 20 local files). Local jpg/png images are limited to 30 MB; mp4/mov videos to 4 GB. Files transfer privately without manual hosting. Images return original width/height/name with image_hash. Batch results preserve input order and report per-file failures; all local files are validated before uploading. Returns image_hash (images) or video_id (videos) for use in zuckerbot_create_ad or a zuckerbot_create_campaign_from_spec IMAGE_SET/VIDEO ref. This is the ONLY supported way to get a usable image_hash: Meta scopes image hashes to a single ad account, so a hash copied out of the Meta business media library or out of a different ad account is rejected at ad-creation time as "Image Not Found". Videos need Meta-side processing: the tool waits briefly and polls; if still processing, call zuckerbot_get_ad_asset_status until ready=true before creating an ad with the video. Library assets are non-delivering and spend nothing. This is the first step for adding a brand-new creative file to an EXISTING (even live) campaign: upload here, then zuckerbot_create_ad into the target ad set.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoOptional library name for the uploaded video
filesNoBatch of local files; mutually exclusive with asset_url and file_path
asset_urlNoPublicly reachable https:// URL; mutually exclusive with file_path and files
file_pathNoAbsolute local jpg/png/mp4/mov path; local stdio/CLI MCP only
asset_typeNoAuto-detected from the URL extension when omitted; pass explicitly for extension-less URLs
business_idNoOptional business ID override for the authenticated API key

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.4.10
    • changedInput schema / properties / asset_url / description
      Previous value: -"Publicly reachable https:// URL of the image or video file (e.g. jpg, png, mp4, mov)"New value: +"Publicly reachable https:// URL; mutually exclusive with file_path and files"
    • addedInput schema / properties / file_path
      Added value: +{
+  "description": "Absolute local jpg/png/mp4/mov path; local stdio/CLI MCP only",
+  "type": "string"
+}
    • addedInput schema / properties / files
      Added value: +{
+  "description": "Batch of local files; mutually exclusive with asset_url and file_path",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "file_path": {
+        "type": "string"
+      },
+      "label": {
+        "maxLength": 100,
+        "minLength": 1,
+        "type": "string"
+      }
+    },
+    "required": [
+      "file_path"
+    ],
+    "type": "object"
+  },
+  "maxItems": 20,
+  "minItems": 1,
+  "type": "array"
+}
    • removedInput schema / required
      Removed value: -[
-  "asset_url"
-]
  2. Addedv0.4.7

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations provided, the description carries the full disclosure burden and does so thoroughly. It covers mutual exclusivity of inputs, file-type and size limits, private transfer, pre-upload validation, batch failure behavior, return shapes, video processing/polling, account-scoped image_hash rejection, and the non-delivering/non-spend nature of assets. Nothing about the tool's side effects or follow-up requirements is hidden.

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?

The description is long but dense, and every sentence earns its place through a constraint, workflow step, caveat, or integration detail. It front-loads the core action and input choices before moving to limits, processing behavior, and downstream usage. There is no filler, tautology, or repetition of the tool name.

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?

With no output schema and no annotations, the description provides a complete operating picture: what sources are accepted, how files are validated, size limits, return values, video-readiness polling, failure modes, and how the output feeds zuckerbot_create_ad or campaign spec references. An agent has enough information to select, invoke, and interpret the tool correctly without additional context.

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

Parameters5/5

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

Although the schema covers 100% of parameters, the description adds critical semantics beyond the schema: accepted image/video formats, 30 MB and 4 GB size limits, the 20-file batch cap, exactly-one-source selection, and the mapping of input type to output artifact (image_hash vs video_id). It also explains how the returned identifiers are consumed downstream, which the schema does not.

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 description opens with a specific verb and resource: 'Upload a NEW image or video file into the connected Meta ad account's library.' It clearly defines accepted sources (https URL or local file path), the batch option, and the concrete output artifacts (image_hash or video_id). This makes the tool's purpose unmistakable and distinguishable from read/status tools like zuckerbot_get_ad_asset_status and creative-analysis siblings.

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

Usage Guidelines4/5

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

It gives strong when-to-use context: this is the ONLY supported way to get a usable image_hash, and it is the first step for adding a new creative to an existing or live campaign. It also routes follow-up video readiness checks to zuckerbot_get_ad_asset_status and later ad creation to zuckerbot_create_ad. It does not explicitly name zuckerbot_upload_creative as an alternative or state when to avoid this tool, so it stops just short of a 5.

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

Deploy Server

Other Tools