---
title: "Call ads.read_board"
method: POST
path: "/api/v1/tools/ads.read_board"
tags: ["ads"]
---

# Call ads.read_board

`POST /api/v1/tools/ads.read_board`

## Request

- Base URL: `https://app.goosybear.ai`
- URL: `https://app.goosybear.ai/api/v1/tools/ads.read_board`
- Auth: HTTP bearer

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.

## Headers

- `x-request-id` string

## Request body

- object
  - `campaign_id` string: The campaign's id. Leave it out to use the campaign the person is looking at.
  - `workspace` string: Which workspace to run in — its slug. Omit to use your default. With more than one reachable workspace and no default, the call is refused and the choices are listed.

## Response `200`

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.

- union
  - object: The tool ran and answered.
    - `ok` true, required
    - `campaign_id` string, required
    - `campaign_name` string, required
    - `platform` string, required
    - `run` 'not_started' | 'drawing' | 'waiting_on_the_ideas' | 'waiting_on_want_more' | 'finished' | 'failed', required: waiting_on_the_ideas: the planned ideas wait for a yes (`ads.draft_creatives`) before any picture is drawn; waiting_on_want_more: the run asks whether to draw more (`ads.more` or `ads.done`).
    - `ideas` string[], required
    - `ads` object[], required
      - `creative_id` string, required
      - `position` integer, required
      - `name` string, required
      - `kept` boolean, required
      - `drawn` boolean, required
      - `headline` string, nullable, required
      - `primary_text` string, nullable, required
      - `description` string, nullable, required
      - `call_to_action` string, nullable, required
    - `daily_budget_cents` integer, required
    - `ad_count` integer, required
    - `live` boolean, required
    - `sizes` object, required: The sizes the platform needs for the kept ads, counted from the campaign's own rows: made of needed, and how many are on their way. When made equals needed every size is done — never say the sizes are still open. Sizes not yet made are Goosy's, made at the approve, never the person's.
      - `made` integer, required
      - `needed` integer, required
      - `drawing` integer, required
    - `starts_on` string, nullable, required
    - `targeting` object, required
      - `audience` string, required
      - `places` string, nullable, required
      - `ages` string, nullable, required
    - `platform_campaign` object, nullable, required
      - `label` string, required
      - `id` string, required
    - `launch` object, required
      - `state` 'not_approved' | 'in_flight' | 'on_platform_paused' | 'on_platform_scheduled' | 'on_platform_live' | 'refused', required: not_approved: nothing has approved this launch and no card is up — on a launch ask call `ads.approve_launch`, which raises the card; when sentence is set the last launch was refused for that reason and approving again retries it. in_flight: approved, and the launch step has not settled — say it is still on its way. on_platform_paused: the platform has it, paused; nothing spends until it is switched on (`ads.switch_campaign`). on_platform_scheduled: switched on, and it starts serving on its start date; nothing spends before then. on_platform_live: switched on and serving; it spends its daily amount until paused. refused: the launch step refused; say its sentence.
      - `provider_campaign_id` string, nullable, required
      - `sentence` string, nullable, required
    - `workspace` string, required: The slug of the workspace this call ran in.
    - `working_in` object, required: Which workspace this call ran in, and how that was decided. Present on every workspace-scoped result.
      - `label` string, required: The chip words — e.g. "working in: Acme Main".
      - `note` string, required: Why this workspace — e.g. "your default", "this call only".
      - `workspace` string, required: The resolved workspace's slug.
      - `source` 'call-override' | 'key-pin' | 'stored-default' | 'sole-reachable', required: Which rung of the R7 precedence resolved the workspace.
  - ToolRefusal: A call that was admitted and dispatched, and did not succeed.
    - `ok` false, required
    - `code` string, required: The typed reason — e.g. `workspace_ambiguous`, `invalid_arguments`, or the tool's own failure code.
    - `message` string, required: A sentence a person can act on.
    - `workspaces` string[]: On a workspace refusal: the slugs this key may pass as `workspace`.
    - `issues` object[]: On `invalid_arguments`: which fields failed, and why.
      - `path` string, required
      - `message` string, required
    - `path` string: On an authoring refusal: where in your call's input it points, e.g. `steps.<key>.params.<field>`.
    - `fix` string: On an authoring refusal: the change to your call that would pass.
    - `instruction` string: On an authoring refusal: what to do next with it.

## Other responses

- `400`: The request could not be used: the body is present but not a JSON object (`tenant_api.malformed_body`); it is a top-level array carrying more messages than this endpoint accepts (`tenant_mcp.batch_too_large`); or the `Idempotency-Key` header is malformed (`tenant_api.idempotency_key_invalid`), disagrees with the body's `idempotency_key` (`tenant_api.idempotency_key_conflict`), or was sent to an action that cannot replay a retry (`tenant_api.idempotency_unsupported`). Nothing ran.
- `401`: No bearer credential, or one that did not resolve. Deliberately ONE undifferentiated answer for absent / unknown / revoked / expired, so the endpoint is never an oracle over the key space.
- `403`: The credential is good but the surface is not open to it — the platform or account API switch is off, or the holder lacks the `api.access` capability. The `code` says which.
- `404`: No such tool. The body names no tool and is identical for every unrecognised name.
- `429`: Over this key's per-minute cap. Carries `Retry-After` and `error.retry_after_seconds`.

---

[API](https://skmtc.dev/goosybear/apis/goosy-bear-api.md) · [All operations](https://skmtc.dev/goosybear/apis/goosy-bear-api/llms.txt) · [OpenAPI document](https://skmtc.dev/goosybear/apis/goosy-bear-api/revisions/6d82fb124064?raw)