LeanrIQ

LeanrIQ Creative Runtime: Default preview mode works without Studio and stores research, briefs, builds, QA, and previews in a LeanrIQ workspace. collaborate keeps proposals non-destructive; operate deliberately creates Studio work. Publish is never inferred: traffic_ready and publish remain explicit governed Studio actions.

launch_creative_campaign

Idempotent

LeanrIQ Creative Runtime: Default preview mode works without Studio and stores research, briefs, builds, QA, and previews in a LeanrIQ workspace. collaborate keeps proposals non-destructive; operate deliberately creates Studio work. Publish is never inferred: traffic_ready and publish remain explicit governed Studio actions.. Classification: writes to Studio, creates billable AI usage, publishes externally. Execution: synchronous. Task support: forbidden. Mutation modes: validate_only, preview_only, execute. Partial failure policy: completed_items_not_rolled_back. The returned JSON is internal application state for LeanrIQ and ChatGPT orchestration. Use assistantSummary first when responding to the user. Never display raw JSON, data, or meta unless the user explicitly asks for raw JSON. Mention IDs only when useful for follow-up or debugging. Prefer concise, human language, highlight the most useful insight, and suggest the next best LeanrIQ action. If idempotencyKey is omitted on a mutation, the MCP layer derives a deterministic retry key from the tool and business arguments so an accidental identical replay cannot create duplicate work. For a mutation when more than one seat is authorised, seatId or seatName must be supplied on that exact tool call; a remembered or previously selected seat is not sufficient for a write.

Input Schema

TableJSON Schema

Name	Required	Default
`KPI`	No
`cta`	No
`tone`	No
`brand`	No
`force`	No
`offer`	No
`budget`	No
`seatId`	No
`channel`	No
`endDate`	No
`product`	No
`audience`	No
`elements`	No
`flightId`	No
`headline`	No
`platform`	No
`seatName`	No
`vertical`	No
`accountId`	No
`mustAvoid`	No
`objective`	Yes
`skippable`	No
`startDate`	No
`approvalId`	No
`campaignId`	No
`flightName`	No
`constraints`	No
`creativeIds`	No
`destination`	No
`funnelStage`	No
`mustInclude`	No
`persistence`	No
`targetSizes`	No
`workspaceId`	No
`advertiserId`	No
`campaignName`	No
`deliverables`	No
`saveToStudio`	No
`executionMode`	No	preview
`idempotencyKey`	No
`landingPageUrl`	No
`sourceAssetIds`	No
`supportingCopy`	No
`thirdPartyTags`	No
`durationSeconds`	No
`revisionRequest`	No
`workspaceSource`	No
`performanceEvidence`	No
`sourceFrameImageUrls`	No
`workspaceAccessToken`	No
`createCampaignIfMissing`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`data`	Yes
`meta`	Yes
`error`	No
`status`	Yes
`assistantSummary`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 6, 2026

addedInput schema / properties / sourceFrameImageUrls

Added value: +{
+  "items": {
+    "maxLength": 4000,
+    "type": "string"
+  },
+  "maxItems": 3,
+  "type": "array"
+}

Changed6 schema fields changedOct 5, 2026

addedInput schema / properties / cta

Added value: +{
+  "maxLength": 500,
+  "minLength": 1,
+  "type": "string"
+}

addedInput schema / properties / durationSeconds

Added value: +{
+  "maximum": 120,
+  "minimum": 5,
+  "type": "integer"
+}

addedInput schema / properties / headline

Added value: +{
+  "maxLength": 500,
+  "minLength": 1,
+  "type": "string"
+}

addedInput schema / properties / skippable
```
Added value: +{
+  "type": "boolean"
+}
```

addedInput schema / properties / sourceAssetIds

Added value: +{
+  "items": {
+    "maxLength": 240,
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 50,
+  "type": "array"
+}

addedInput schema / properties / supportingCopy

Added value: +{
+  "maxLength": 500,
+  "minLength": 1,
+  "type": "string"
+}

Changed1 schema field changedOct 2, 2026

addedInput schema / properties / creativeIds

Added value: +{
+  "items": {
+    "maxLength": 240,
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 24,
+  "minItems": 1,
+  "type": "array"
+}

Changed1 schema field changedSep 30, 2026

addedInput schema / properties / thirdPartyTags

Added value: +{
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "creativeId": {
+        "maxLength": 240,
+        "minLength": 1,
+        "type": "string"
+      },
+      "name": {
+        "maxLength": 240,
+        "minLength": 1,
+        "type": "string"
+      },
+      "tag": {
+        "maxLength": 12000,
+        "minLength": 1,
+        "type": "string"
+      }
+    },
+    "required": [
+      "tag"
+    ],
+    "type": "object"
+  },
+  "maxItems": 3,
+  "type": "array"
+}

First observedAug 12, 2026

TDQS

B3.1/5.0

Behavior4/5

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

Substantially exceeds the annotations: classification as writing to Studio, creating billable AI usage, and publishing externally; synchronous execution; task support forbidden; mutation modes; partial failure policy (completed_items_not_rolled_back); deterministic idempotency-key derivation when omitted; and a hard seatId/seatName requirement on writes. Annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false, openWorldHint=true) are consistent with this, and the description adds real consequence detail beyond them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

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

The labeled clauses (Classification, Execution, Mutation modes, Partial failure policy) are well-structured and front-load the mode semantics. But the first two sentences duplicate the title verbatim (including a stray double-period), and orchestration/response-formatting boilerplate crowds out tool-specific information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex, 51-parameter, high-consequence mutation the description covers governance, failure semantics, idempotency, and seat preconditions, and an output schema exists so return values needn't be spelled out. The remaining shortfall is that most parameters are still opaque. Reasonable but not complete.

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

Parameters2/5

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

Schema coverage is 0% across 51 parameters, so the description must carry parameter meaning, and it only explains a handful of governance-critical ones (executionMode modes, seatId/seatName, idempotencyKey). Core inputs like objective, brand, budget, creativeIds, persistence/saveToStudio, and the many date/target fields get no semantic explanation at all, leaving the bulk of the surface undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The name says launch_creative_campaign, but the description leads with runtime/mode lore ("Default preview mode works without Studio and stores research, briefs, builds, QA, and previews") rather than plainly stating that it launches a creative campaign. The actual verb+resource is only inferable, and no sibling (build_ad, build_campaign_creative_set, run_creative_chain, leanriq_launch_creative_campaign) is distinguished. Adequate but muddy.

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

Usage Guidelines3/5

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

It does define mode-selection semantics: collaborate keeps proposals non-destructive, operate creates Studio work, and publish/traffic_ready are explicit governed actions. However, it gives no guidance on when to pick this tool over the many overlapping build_*/run_creative_chain siblings, and no exclusions.

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

All LeanrIQ 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?