Skip to main content
Glama

Ads Uploader: Meta Ads MCP

Get Upload Status

ads_get_upload
Read-onlyIdempotent

Get a completed upload batch by batchId (or its alias uploadId), or poll a background media-ingest job by jobId until complete is true. Job polls return the full result, progress and file list by default; pass compact:true for counts and failed files only.

Input Schema

NameRequiredDescriptionDefault
jobIdNoBackground ingest job ID. Poll until complete is true; the final batch summary is returned in result.
batchIdNoCompleted upload batch ID.
compactNoOpt in to counts and failed files for jobId polls. Default false returns the full result, progress and files.
uploadIdNoAlias for batchId. ads_upload returns batchId; ads_create calls that same batch ID uploadId. The per-file multipart uploads[].uploadId in a presigned ads_upload response is a storage upload ID used by ads_upload_finalize, NOT a batch ID, and must not be passed here.
accountIdNoOptional ad account ID, e.g. act_123.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and non-destructive, so the safety profile is covered. The description adds behavior the annotations cannot convey: polling semantics (repeat until complete is true), the default return payload (result, progress, file list), the compact opt-in reducing to counts and failed files, and the warning that a presigned upload's uploads[].uploadId is a storage ID, not a batch ID. It stops short of describing error or not-found behavior, so not a 5.

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?

Two sentences, front-loaded with the identifier-selection rule before the return-shape detail. Every clause carries information an agent needs — mode selection, polling condition, default payload, and the compact override — with no filler or restatement of the title.

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?

No output schema exists, so the description must carry return-value information, and it does: full result, progress and file list by default versus counts and failed files under compact. Polling termination and the identifier footguns are covered. It does not describe what a non-complete or failed job response looks like, which is the main remaining gap for a polling tool.

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% and each property already carries a description covering jobId polling, the batchId/uploadId alias, and compact defaults, so the schema does most of the work. The description reinforces the compact true/false trade-off and the alias relationship but introduces little that is not already in the schema text. Baseline 3 is appropriate.

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 (get/poll) and two precisely-scoped resources: a completed upload batch addressed by batchId/uploadId, and a background media-ingest job addressed by jobId. The dual-mode structure is spelled out so an agent can tell immediately which branch applies, and the alias relationship is defined rather than assumed.

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?

Gives clear conditional guidance: use batchId for a finished batch, uploadId as its alias, and jobId to poll a background ingest until complete is true. It also flags when NOT to pass a value — the per-file multipart uploads[].uploadId — which is a real routing error it prevents. It does not name a sibling alternative for job status, but the surrounding guidance is still sufficient to select correctly.

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.