Skip to main content
Glama

Manage Smart Campaign Draft Creative

dynamoi_manage_smart_campaign_creative
Destructive

Use save_setup with setupSave={playLinkId, appleMusicUrl?} and a stable UUID-v4 setupRequestId per setup flow; reuse it on retries, and start a new flow for different content. It returns setupDraft. Use read_budget for budgetDraft and save_budget with budgetSave={campaignId, expectedUpdatedAt, budgetAmountCents, budgetAmountMinor?, currency?, budgetType:DAILY|TOTAL, endDate:YYYY-MM-DD|null}. Amounts are exact minor units in the artist currency; use the budget policy from read_budget. Setup and budget saves only edit drafts and never launch or charge. Use read_location to read native draft targeting and save_location with locationSave={campaignId, expectedUpdatedAt, targeting:{mode:WORLDWIDE}|{mode:INCLUDE,countryCodes:[US]}} to save it. Read locationDraft first for the current revision; both location actions return locationDraft. Read generation progress, generated creatives and current selection with action=read. To discover owned social posts, explicitly add catalog={source:facebook|instagram,limit:1..25,after?:nextCursor}. Only requested catalog reads fetch connected-account posts; use catalog.items[].id directly in selectedSocialPosts. Pass nextCursor as after for another page. Catalog reads never alter selections, token state, or campaigns; provider failure is an error, and selection revalidates ownership. Use start_generation, retry_generation or clear_generation with campaignId and expectedUpdatedAt from read. Generation runs asynchronously; poll with read. Use source_audio_upload_status or abort_source_audio_upload with campaignId, expectedUpdatedAt, uploadId and uploadSessionId to inspect uploaded parts or abort the direct upload. Agents never approve or submit. Use action=select with campaignId and expectedUpdatedAt from read, source=generate|posts|upload, and selectedCreativeIds, selectedSocialPosts (owned META:post IDs), or uploadedAssets=[{mediaAssetId}] from dynamoi_list_media_assets. Omit selectedCreativeIds for social or uploaded media. Uploaded metadata is resolved by the server; only owned, moderation-approved uploads can be selected. Selection never attests artist approval and never submits the campaign. Upload private JPEG/PNG/MP4 campaign media (1 GiB maximum) with start_media_upload, campaignId, expectedUpdatedAt and mediaUpload={assetId:UUID,fileName,fileSizeBytes,contentType}. Retain the returned key/uploadId and PUT each presigned part URL. Complete with complete_media_upload, a freshly inspected expectedUpdatedAt, and mediaUpload={assetId,fileName,fileSizeBytes,fileType,key,uploadId,parts:[{partNumber,etag}]}. Use media_upload_status or abort_media_upload with campaignId and mediaUpload={key,uploadId}; both remain usable after draft edits. A completed status means retry completion, not re-upload. Completion returns only a moderation receipt; poll dynamoi_list_media_assets and select only after APPROVED. Uploads do not edit the draft selection. Attach source MP3 audio to a draft with start_source_audio_upload, PUT each returned presigned part URL, then complete_source_audio_upload with the returned uploadId/uploadSessionId and part ETags. Both actions require campaignId, expectedUpdatedAt, fileSizeBytes, trackDurationSeconds and 0–2 hookSeconds. Read sourceAudio to confirm. Use import_source_audio with a public Dropbox share url, campaignId, expectedUpdatedAt, trackDurationSeconds and 0–2 hookSeconds (250 MiB maximum). Google Drive is unsupported because it requires a Google API key. On timeout or an ambiguous result, re-read sourceAudio before retrying.

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": {
      "action": "<action>",
      "artistId": "<artistId>"
    },
    "name": "dynamoi_manage_smart_campaign_creative"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNo
partsNo
actionYes
sourceNo
catalogNo
artistIdYes
uploadIdNo
setupSaveNo
budgetSaveNo
campaignIdNo
hookSecondsNo
mediaUploadNo
locationSaveNo
fileSizeBytesNo
setupRequestIdNo
uploadedAssetsNo
uploadSessionIdNo
expectedUpdatedAtNo
selectedCreativeIdsNo
selectedSocialPostsNo
trackDurationSecondsNo

Output Schema

NameRequiredDescriptionDefault
codeNo
dataNo
kindNo
fieldNo
statusYes
draftIdNo
messageNo
retryableNo
nextActionNo
failureStageNo
prerequisiteNo
screeningResultNo
retryAfterSecondsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / selectedCreativeIds / maxItems
      Previous value: -100New value: +10
    • changedInput schema / properties / uploadedAssets / maxItems
      Previous value: -30New value: +10
  2. Added

TDQS

A3.9/5.0
Behavior5/5

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

Beyond the annotations (destructiveHint=true, openWorldHint=true), the description discloses the crucial behavioral facts: setup and budget saves only edit drafts and never launch or charge, agents never approve or submit, selection never attests artist approval, catalog reads never alter selections or token state, and only owned moderation-approved uploads can be selected. It also gives idempotency (stable setupRequestId per flow), concurrency (expectedUpdatedAt re-inspection), size ceilings (1 GiB media, 250 MiB audio) and the unsupported-provider caveat for Google Drive.

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?

Length is defensible for a nineteen-action mega-tool and almost every sentence carries operational content, but the text is one unstructured wall with no headings, grouping, or front-loaded summary. An agent must parse linearly to find the action it needs, and there is no opening line to orient it.

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?

Given 19 actions, 21 parameters and an existing output schema, the description covers behavior, sequencing, limits and failure handling thoroughly. It stops short of complete because artistId (a required parameter on every call) is never referenced and there is no high-level framing of the draft lifecycle the actions belong to.

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 description coverage is 0% across 21 params, so the description must carry the burden and largely does: it explains setupSave, budgetSave fields (with the 'exact minor units in artist currency' and budget-policy rule), locationSave targeting modes, catalog paging via after/nextCursor, mediaUpload fields and part ETags, and the mutual exclusivity of selectedCreativeIds/selectedSocialPosts/uploadedAssets. Gaps remain for top-level url, parts and source, and the required artistId is never mentioned at all.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description enumerates the nineteen actions (setup, budget, location, generation, selection, media/source-audio uploads) but never opens with a plain statement of what the tool is for. An agent can infer 'manage smart campaign draft creative' only by reading action names and payload shapes, and nothing distinguishes it from siblings such as dynamoi_smart_campaign_ad_copy or dynamoi_get_campaign.

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?

Each action carries explicit usage rules: read_budget before save_budget, read_location before save_location, omit selectedCreativeIds for social/uploaded media, and poll action=read after start_generation. Retry and edge-case routing is also spelled out ('re-read sourceAudio before retrying', 'a completed status means retry completion, not re-upload'). What is missing is guidance on when to reach for this tool versus the sibling campaign tools.

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.