Call ads.read_board
Read a campaign's targeting, sizes and launch — 'what is it targeting', 'who sees it', 'did it land on Meta?', 'where do the ad sizes stand?'. Returns its targeting (who it reaches, the places it runs and the age band), its ads, each by its creative_id with its words and whether it is kept and drawn, the planned ideas while they wait for a yes, what the campaign's ads run is doing now, its sizes made of needed, its start date, and where its launch is — waiting on an approve, still on its way, on the platform paused with the platform's own campaign id, or refused with the reason. Call it in this turn for every question about who the campaign reaches or where it runs ('where does it run'), its ads ('what ads do we have'), its sizes or an approved launch ('did it launch?', 'did it go through?'), and answer from this read — never from an earlier reply, and never by raising the launch card again. Leave campaign_id out to read the campaign on screen; the platform's own campaign id is never a campaign_id. Call it before keeping, setting aside or rewording ads by their place ('the first one'), so each is named by its creative_id. It reads only: it changes, draws and spends nothing — when they asked to keep, set aside or reword, call ads.keep or ads.set_words next, in the same turn, and say it is done only from that tool's result. Not for whether the campaign is ready to launch — that is ads.launch_check.
Every result names the workspace it ran in. Say which workspace the answer is about. When the account has more than one workspace and none is selected, this tool refuses with workspace_ambiguous and lists the choices — offer them, never pick one.
Request
- Base URL: https://app.goosybear.ai
- URL: https://app.goosybear.ai/api/v1/tools/ads.read_board
- Auth: HTTP bearer
Headers
Your own id for this request, echoed back and recorded on the audit trail. 1–128 characters from A–Z a–z 0–9 . _ : -, starting with a letter or digit; anything else is replaced by a generated id.
Request body
Response
The call was admitted and dispatched. ok says whether the tool succeeded — a refusal the tool itself produced is still a 200, exactly as it is a successful JSON-RPC result over MCP.
Changes
No recorded changes to this operation across all 6 revisions of this API.