mcp-server

configure_ad_step

Destructive

Configure ONE step of an ad's setup wizard and save it. Saving a step never activates or publishes: the summary step is refused here — finish setup with activate_ad. Use this to set up an ad step by step IN ORDER, repeatedly targeting each step the previous result reported as nextStepType, until nextStepType is 'summary' (then call activate_ad). Identify the step by step_index (from get_ad steps[].index) — step_type alone targets the FIRST step of that type. Out-of-order calls return 'prerequisite_not_met' / 'step_not_available'. CONNECTION IS NOT CONFIGURABLE HERE: the connection/auth step (credentials, API keys, OAuth) can never be set through MCP. 'oauth_required' / 'credentials_in_ui' is TERMINAL — hand the returned oauthUrl or editUrl to the USER, then STOP and wait; do NOT resend the step, guess field codes or retry. Returns {integrationId, stepType, status, ready, lastStep, nextStepType, oauthUrl, transitions[], message}; status is 'saved', 'oauth_required', 'credentials_in_ui', 'prerequisite_not_met', 'step_not_available' or 'validation_failed'. A product export/generation and a deferred category-attribute download run ASYNC — poll ad_status (productsRefreshing, productsSubmitting, categoryAttributeWarmup) before trusting counts or reading the attribute list. A dropdown field takes options[].value, never its position in the list. Full walkthrough (every step type's payload, the product-filter flags, optionsPending, the deferred-attribute branch): call get_koongo_help with slug 'ad-wizard-steps'. ad_id is from list_ads / create_ad. project_id is OPTIONAL (inferred for a single-project customer; project_id_required otherwise — then call list_projects).

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": {
      "ad_id": "<ad_id>"
    },
    "name": "configure_ad_step"
  }
}

Input Schema

Name	Required	Description
`ad_id`	Yes
`payload`	No	Settings for this step. Form / order-settings: {items: {fieldCode: value}} from get_ad steps[].fields. A connection/auth step takes NO payload and cannot be configured here — omit it (also for advance-only steps).
`step_type`	No	Target the step by type (the nextStepType from the previous step). Ambiguous when two steps share a type — then pass step_index.
`project_id`	No
`step_index`	No	Target the step by its index (get_ad steps[].index) — use this to disambiguate steps that share a step_type.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 3, 2026

changedInput schema / properties / step_type / description

Previous value: -"Target the step by type (the nextStepType from the previous step). Ambiguous when two steps share a type — prefer step_index."New value: +"Target the step by type (the nextStepType from the previous step). Ambiguous when two steps share a type — then pass step_index."

First observedSep 1, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Beyond the mutation-related annotations, it discloses that saving never activates or publishes, out-of-order calls fail with named statuses, and OAuth or UI-credential states are terminal and must not be retried. It also explains asynchronous product and category-attribute work, the returned status model, and the need to poll before trusting counts or attributes.

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?

The most important facts—single-step scope, non-publication, activation routing, and ordered usage—are front-loaded, and nearly every sentence addresses a real invocation risk. However, the definition is a long, dense single paragraph; separating workflow, errors, asynchronous behavior, and parameter guidance would improve scannability.

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 complex stateful wizard with a nested payload and no output schema, the description supplies the return fields, status vocabulary, targeting rules, failure handling, activation boundary, and asynchronous follow-up requirements. It also routes agents to get_ad, list_ads, create_ad, list_projects, ad_status, activate_ad, and the detailed help document at the appropriate points.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds substantial operational meaning beyond the 60% schema coverage: ad_id comes from list_ads or create_ad, step_index comes from get_ad, and step_type alone selects the first matching step. It further explains project_id inference and failure behavior, dropdown option values, and points to detailed payload documentation for individual step types.

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?

The opening sentence precisely identifies the operation and scope: configure and save one step of an ad's setup wizard. It clearly distinguishes this tool from activate_ad and excludes connection/auth configuration, so its role among the sibling tools is unambiguous.

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?

It provides an explicit workflow: configure steps in order using the previous result's nextStepType, stop at summary, and call activate_ad. It also gives precise guidance for OAuth and UI-credential terminal states, asynchronous polling through ad_status, and where to obtain the full walkthrough.

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

All mcp-server 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.

Resources

Need Help?