Tailwind App

regenerate_pin_design

Use this to have Tailwind's AI generate a NEW design for an AI-designed (premium) Pin. Asynchronous and metered: it spends about 7 of the user's plan credits, takes a few minutes, and returns an id to poll with get_design_regeneration_status. Only works when get_pin_design lists "regenerate" in supportedOperations.

Because it spends the user's credits, confirm with the user before calling it, and say what it will cost. Calling it again after one finishes starts and charges ANOTHER regeneration, so poll before retrying.

The result does NOT replace the Pin's design on its own: a finished regeneration returns a variationUrl that you then pass to select_pin_design_variation. Tell the user the new design is ready and let them choose, rather than applying it silently. Afterwards get_pin_design reports workspaceStatus pending_apply with the new design as pendingMediaUrl; that is the expected resting state, not a failure, and it stays that way until the user picks the design.

To REVISE the design the Pin already has, rather than replace it, pass selectedVariationUrl as well: the active variation's templateImageUrl from get_pin_design. Without it the generator has nothing to revise and produces an unrelated design for the same credits, which is rarely what someone asking to adjust their current design wants. If the user did not say which Pinterest account to use and list_accounts returns more than one, ask the user which account to use before calling this — do not choose for them.

Input Schema

Name	Required	Description
`title`	No	Text to overlay on the new design. This is not the Pin's title.
`postId`	Yes	Pin ID from list_posts
`mediaUrl`	No	Publicly reachable image to generate the new design from, such as a URL from get_pin_design's sourceImageCandidates
`uploadId`	No	Image staged with create_media_upload. Use instead of mediaUrl, not with it.
`accountId`	Yes	Numeric Tailwind account ID from list_accounts
`premiumStyle`	No	Visual style for the new design. Defaults to the Pin's existing style.
`userFeedback`	No	What to change, in the user's own words (e.g. 'make the text bigger and use warmer colors')
`selectedVariationUrl`	No	The design to revise: the active variation's templateImageUrl from get_pin_design. Pass it whenever the user wants their current design adjusted. Omit it only to generate a fresh, unrelated design.

Output Schema

Name	Required	Description	Default
`regeneration`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 21, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already mark this as non-read-only, non-idempotent, and open-world, but the description adds critical behavior: asynchronous, takes a few minutes, spends about 7 credits, repeated calls charge again, and the result does not automatically replace the Pin's design. It also explains the pending_apply resting state so the agent doesn't mistake it for failure.

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 description is long, but the cost and async nature are front-loaded, and the multi-step workflow justifies most of the length. A few points are repeated for emphasis (credits, polling, confirmation), but each paragraph carries distinct operational guidance.

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 costly, asynchronous, multi-step tool with an output schema, the description covers the full lifecycle: precondition check, credit confirmation, polling, variation selection handoff, and expected pending_apply state. An agent has everything needed to invoke it correctly without guessing.

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

Parameters4/5

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

Schema description coverage is 100%, so the baseline is 3. The description goes beyond the schema for the most consequential parameter, selectedVariationUrl, by explaining that omitting it produces an unrelated design rather than a revision, and it also clarifies that account selection should be confirmed with the user. This adds meaningful semantic guidance beyond the field-level descriptions.

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?

States a specific verb and resource: generate a NEW AI design for a premium Pin using Tailwind's AI. It distinguishes this from revising an existing design and from applying a design via select_pin_design_variation, so an agent can tell it apart from sibling tools.

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?

Gives explicit preconditions ('only works when get_pin_design lists regenerate in supportedOperations'), cost-confirmation guidance, retry guidance ('poll before retrying'), and an account-selection rule when list_accounts returns multiple accounts. It clearly explains when to pass selectedVariationUrl versus when to omit it.

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

All Tailwind App 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?