[AdCP Deterministic Testing] Force state transitions for compliance runs. Sandbox accounts only; live accounts get FORBIDDEN. scenario=list_scenarios enumerates.
| Name | Required | Description | Default |
|---|---|---|---|
| params | No | ||
| account | No | ||
| scenario | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of behavioral disclosure. It clearly communicates the sandbox-only restriction and the FORBIDDEN outcome on live accounts, which is important safety-relevant behavior. However, it does not explain side effects of forcing state transitions, whether the operation is reversible, or what the response looks like.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is short and front-loaded with the tool's purpose and domain. The 'scenario=list_scenarios enumerates' phrasing is slightly cryptic, but the overall structure wastes no words and delivers the most critical constraints compactly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a state-mutating test controller with no annotations and no output schema, the description is incomplete. It omits return values, side effects, and the meaning of the 'params' and 'account' parameters, leaving an agent without enough information to invoke the tool confidently beyond the sandbox constraint.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate for parameter meaning. It adds useful meaning for 'scenario' by indicating the 'list_scenarios' value to enumerate options, but leaves the 'params' and 'account' nested objects completely unexplained despite their presence in the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific action ('Force state transitions') on a specific resource ('compliance runs'), and the '[AdCP Deterministic Testing]' prefix adds domain context. It does not explicitly differentiate from sibling tools, but the action is distinctive enough among the listed siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives explicit usage constraints: sandbox accounts only, with live accounts receiving FORBIDDEN. It also provides a practical entry point via 'scenario=list_scenarios enumerates', though it does not discuss alternatives because none are clearly related.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
There are exact duplicates (get_task_status/tasks_get, list_tasks/tasks_list) and several overlapping analytics, attribution, and semantic search clusters (get_attention_metrics vs get_creative_attention vs get_social_attention; find_similar_moments vs semantic_search_observations; get_campaign_attribution vs get_multi_touch_attribution vs get_roas). Detailed descriptions help, but with 83 tools an agent will frequently struggle to pick the right one.
Most tools follow a snake_case verb_noun pattern (list_devices, create_campaign, delete_webhook), but there are notable inconsistencies: list_* and get_* are used interchangeably for list operations, attention tools mix conventions (get_attention_metrics vs get_creative_attention vs get_social_attention), and the legacy tasks_get/tasks_list names break the established get_task_status/list_tasks pattern.
83 tools is an extreme count for a single MCP server, spanning device management, sensing, campaigns, media buys, attribution, webhooks, billing, API discovery, and AdCP protocol concerns. This is a broad API surface dump rather than a focused tool set, and it would be far better split into several coherent servers.
Despite the enormous surface, core campaign lifecycle is incomplete: create_campaign explicitly tells the agent to use update_campaign to activate a campaign, but no update_campaign tool exists, and there are no list/delete campaign tools. Significant capabilities exist for analytics, attribution, and webhooks, but the primary advertising workflow has a dead end.