GrowSurf MCP Server

Official

by growsurf

Overview Schema Source Related Servers Discussions Admin

TypeScript

Hybrid

Update Program Design

growsurf_update_campaign_design

DestructiveIdempotent

Update GrowSurf program design settings, including participant avatars, claim offer popup, website widget, traffic insights, sign-in copy, payout confirmation, and settings panel.

Instructions

Update the design configuration for your GrowSurf program, including participant avatars under participantAvatarStyle, referred-visitor content such as the Claim Offer Popup, the website widget under widget (button or card, placement, timing, and visible pages), the participant Traffic report under trafficInsights, participant sign-in copy under login, payout-destination confirmation page copy under payoutDestinationConfirmation, and the participant Settings panel under participantSettings, such as the language picker's languageSectionTitle and languageSectionInstructionsText (up to 500 characters each). trafficInsights.isPublicDisplayed controls visibility; its labels cannot be blank. participantAvatarStyle accepts CHARACTERS, INITIALS, ANIMALS, or GRADIENT. Only supplied fields change; omitted fields retain their existing content and arrays replace wholesale. Targets campaignId if supplied, otherwise GROWSURF_CAMPAIGN_ID.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`fields`	Yes
`campaignId`	Yes	Target program (campaign) id for this call. Defaults to GROWSURF_CAMPAIGN_ID when omitted. Program IDs also identify newly created programs without restarting the server.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.19.15Oct 15, 2026
- addedInput schema / properties / campaignId / minLength
```
Added value: +1
```
- changedInput schema / required
```
Previous value: -[
-  "fields"
-]New value: +[
+  "fields",
+  "campaignId"
+]
```

Changed1 schema field changedv0.19.9Oct 3, 2026

changedInput schema / properties / campaignId / description

Previous value: -"Target program (campaign) id for this call. Defaults to GROWSURF_CAMPAIGN_ID when omitted. Pass the `id` returned by growsurf_create_campaign to configure or operate a program you just created, without restarting the server."New value: +"Target program (campaign) id for this call. Defaults to GROWSURF_CAMPAIGN_ID when omitted. Program IDs also identify newly created programs without restarting the server."

First observedv0.12.2Aug 25, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=true, yet the description adds meaningful behavior: partial-merge semantics with wholesale array replacement, the constraint that trafficInsights labels cannot be blank, the 500-character limit on language-section copy, and the environment-variable default for campaignId. What it does not add is the concrete destructive consequence of a partial update (what an overwritten array loses) or any auth/permission requirement.

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?

Front-loaded with the action and scope, and every clause conveys usable information (field names, enums, limits, merge rules) rather than filler. It is a single dense paragraph of long comma-separated lists, however, when bulleted grouping by sub-area would have scanned faster.

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 nested, open-ended `fields` payload, the description covers what can be changed, the enum domain, validation limits, array-replacement semantics, and id-vs-env-var targeting. An output schema exists, so return values need no explanation, and nothing required to call the tool correctly is missing.

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?

Schema coverage is only 50% and the `fields` object is declared as an opaque additionalProperties bag with no documented sub-keys, so the description carries the real burden: it names the accepted shapes, the enum values for participantAvatarStyle (CHARACTERS, INITIALS, ANIMALS, GRADIENT), and the specific nested paths like trafficInsights.isPublicDisplayed and participantSettings.languageSectionTitle. This is far more than the schema provides.

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 ('Update') and resource ('design configuration for your GrowSurf program') and enumerates the exact sub-areas it governs (participantAvatarStyle, widget, trafficInsights, login, payoutDestinationConfirmation, participantSettings), which cleanly separates it from siblings like growsurf_update_campaign_options and growsurf_update_campaign_emails. An agent can identify the tool's domain without opening the schema.

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?

Usage is implied by the field-level scope, and merge behavior ('Only supplied fields change; omitted fields retain their existing content') tells the agent how to invoke it, but there is no explicit when-to-use/when-not guidance and no sibling named as the alternative (e.g., get_campaign_design for reading, or the options/emails tools for other program sections).

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

Deploy Server