StealAds

Get creative copy and history

get_creative_workspace

Read-onlyIdempotent

Returns the copy of one finished image ad: the original and current headline, primary text and call to action, any pending rewrite proposal, and up to 25 revision history entries per page with next_cursor. The read that follows revise_copy and precedes applying, discarding, undoing or editing copy. Takes a generation_job_id, not the job reference that get_ad_status takes; list_generation_jobs returns both. Campaign images are read with get_campaign_output_workspace instead.

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": {
      "generation_job_id": "<generation_job_id>"
    },
    "name": "get_creative_workspace"
  }
}

Input Schema

Name	Required	Description
`cursor`	No	next_cursor from the previous history page of the same ad; absent for the first page.
`response_format`	No	Output format: text (default) or json. table is not available for this tool.
`generation_job_id`	Yes	Finished-image reference of a single ad: _references.generation_job_id on a list_generation_jobs row. Not the job_id that get_ad_status takes.

Output Schema

Name	Required	Description
`current`	No	Currently selected ad copy.
`history`	No	Bounded copy revision history.
`pending`	No	Revision awaiting delivery or selection.
`baseline`	No	Original copy before revisions.
`has_more`	No	Whether another bounded page is available with next_cursor.
`_references`	No	Opaque action references accepted by subsequent tool calls.
`manual_edit`	No	Whether manual copy changes are available, with field length constraints.
`next_cursor`	No	Continuation handle for the same filters; null when no further page is offered.
`cost_credits`	No	Credits quoted or charged by this operation.
`current_version_id`	No	current version id value in this response.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedNov 10, 2026

changedInput schema / properties / cursor / description

Previous value: -"Continuation handle from the same tool and filters; absent for the first page."New value: +"next_cursor from the previous history page of the same ad; absent for the first page."

changedInput schema / properties / generation_job_id / description

Previous value: -"Generated image reference from list_generation_jobs or get_campaign_outputs."New value: +"Finished-image reference of a single ad: _references.generation_job_id on a list_generation_jobs row. Not the job_id that get_ad_status takes."

changedInput schema / properties / response_format / description

Previous value: -"Output format: text or json for capped research examples; table is available only for tracked rival rows."New value: +"Output format: text (default) or json. table is not available for this tool."

First observedNov 9, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the description is not needed for safety; it instead adds substantive behavior — 25 history entries per page with next_cursor, inclusion of any pending rewrite proposal, and per-ad scope. It does not mention anything about rate limits or freshness of 'current' copy, which is why it is 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.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Content is front-loaded: return shape first, then workflow position, then ID disambiguation, then the alternative tool. It is dense but every clause carries information; the first sentence is long and could be split for scanability, but nothing is filler.

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?

For a read-only lookup with a full output schema, the description covers everything an agent needs: what it returns, pagination via next_cursor, which ID to supply, which tool gives that ID, and which tool to use for campaign images. Return-value detail is a bonus rather than a requirement here because an output schema exists.

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 description coverage is 100%, and the schema itself already says generation_job_id is 'Not the job_id that get_ad_status takes.' The description's main parameter clarification (generation_job_id vs. job reference) therefore largely duplicates the schema; only the pointer to list_generation_jobs returning both references adds new meaning. It also omits the response_format 'table is unavailable' nuance, though that is documented in the schema.

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?

Opens with a specific verb+resource ('Returns the copy of one finished image ad') and enumerates exactly what is returned: original/current headline, primary text, CTA, pending rewrite proposal, and paged history. It also explicitly distinguishes itself from three siblings (get_ad_status, list_generation_jobs, get_campaign_output_workspace).

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

Usage Guidelines5/5

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

States the exact position in the workflow ('the read that follows revise_copy and precedes applying, discarding, undoing or editing copy'), which tells the agent both when to use it and when not to. It further routes the agent to get_campaign_output_workspace for campaign images, so the boundary with the nearest sibling is explicit.

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

All StealAds tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.