ChiefLab

chieflab_regenerate_visual_asset

P72 — regenerate a single visual asset (LinkedIn graphic, X graphic, landing hero, etc.) with a different style / fidelity / headline / model. USE WHEN a reviewer hits 'Regenerate' on a launch image in the Launch Room. Reads the original launch's brief from the run metadata, calls produceVisualAsset with the new parameters, and returns the updated asset shape (assetId, dataUrl, dimensions, prompt, mode). Does NOT auto-persist back to the run — caller decides whether to swap the asset in place (via runStore) or treat the regen as a parallel candidate.

Input Schema

TableJSON Schema

Name	Required	Description
`cta`	No	Override the CTA text.
`seed`	No	Optional seed string for deterministic layout-hint picking.
`model`	No	gemini-2.5-flash-image \| gemini-3-pro-image-preview. Caller override; defaults to the model the brief's fidelity selects.
`runId`	Yes	Launch run id that produced the original asset. Used to look up the LaunchIntelligenceBrief stored on the run.
`style`	No	clean \| bold \| editorial \| playful. Defaults to 'editorial'.
`assetId`	No	Optional original assetId — when present, the regenerated asset reuses the id so the run viewer can swap in place.
`channel`	Yes	Channel the asset is for (linkedin / x / email / landing_hero / etc.).
`fidelity`	No	on_brand \| polished \| experimental. Defaults to 'on_brand'.
`headline`	No	Override the headline rendered into the image.
`brandColors`	No	Optional {primary, accent, bg, text} hex override.
`subheadline`	No	Override the subheadline.
`workspaceId`	No	Optional workspace id.

TDQS

A5/5.0

Behavior5/5

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

With no annotations provided, the description fully discloses the tool's behavior: it reads the original brief, calls produceVisualAsset, returns an asset shape, and does not persist. It also explains that providing assetId allows in-place swapping.

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

Conciseness5/5

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

Single paragraph with front-loaded purpose and usage, no extraneous words. Every sentence adds value.

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?

Given 12 parameters, no output schema, and no annotations, the description fully covers the tool's operation, return value, and decision points, making it complete for correct selection and invocation.

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 significant context beyond the schema, including default values for style and fidelity, explanation of how assetId is reused, and clarification that caller override for model defaults to the brief's selection. Schema coverage is 100% but description enriches it.

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 description clearly states the tool regenerates a single visual asset with different style/fidelity/headline, and specifies the exact use case (when a reviewer hits 'Regenerate'). It also distinguishes from siblings like chieflab_review_visual_asset.

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?

Explicitly says 'USE WHEN a reviewer hits 'Regenerate' on a launch image' and notes that it does NOT auto-persist back to the run, providing clear guidance on when to use and what the caller must do afterward.

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

All ChiefLab tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.7/5.0

Disambiguation4/5

Most tools have distinct purposes, e.g., approve_action vs execute_approved_action vs publish_approved_post. However, alias overloading (e.g., chieflab_launch_product and chieflab_get_users_after_build pointing to the same handler) introduces some ambiguity. The detailed descriptions mostly mitigate confusion, but an agent might still struggle to choose between near-identical aliases.

Naming Consistency4/5

Tools predominantly follow a 'chieflab_verb_noun' pattern (e.g., chieflab_approve_action, chieflab_connect_provider). A few exceptions exist (chieflab_help, chieflab_inbox, chieflab_boot) that are single nouns, but these are clearly distinct and the overall consistency is high.

Tool Count3/5

32 tools is on the high side for an MCP server, but the domain of a growth/marketing launch platform naturally requires many operations (launch, approve, execute, measure, iterate, connect providers, etc.). The count is borderline but still manageable; it doesn't reach the 50+ extreme.

Completeness4/5

The tool set covers the full launch lifecycle: create, approve, execute, measure, and iterate. It includes provider connections, manual fallback, brain summary, and work requests. Minor gaps exist (e.g., no explicit tool for deleting a launch or revoking approval), but core workflows are fully supported.

Resources

Need Help?