Skip to main content
Glama
GrowSurf MCP Server

GrowSurf MCP Server

Official

Bulk Delete Participants

growsurf_bulk_delete_participants
DestructiveIdempotent

Permanently delete up to 200 GrowSurf participants by ID or email in one request, with per-row results for deleted, not-found, duplicate, and error outcomes.

Instructions

Bulk delete participants from your GrowSurf program in one request. DESTRUCTIVE: deletion is permanent and cannot be undone. Successful rows lose participant access immediately; related record cleanup completes automatically, subject to required financial record retention. Each entry in participants is a GrowSurf participant ID or an email address (mixed lists are allowed), up to 200 entries per request — chunk larger lists across multiple calls. Returns a summary (total, deletedCount, notFoundCount, duplicateCount, errorCount) plus per-row results in request order, each with status DELETED, NOT_FOUND, DUPLICATE (resolves to the same participant as an earlier entry), or ERROR — both 200 and 202 responses can include NOT_FOUND or ERROR rows, and the summary reports these outcomes. A 202 response includes analyticsErasure when analytics erasure is pending. DELETED means participant access was removed; reports can retain the participant until cleanup completes. Do not repeat successful rows to finish cleanup. Targets campaignId if you pass it, otherwise GROWSURF_CAMPAIGN_ID.

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": {
      "participants": "<participants>",
      "campaignId": "<campaignId>"
    },
    "name": "growsurf_bulk_delete_participants"
  }
}

Input Schema

NameRequiredDescriptionDefault
campaignIdYesTarget program id for this call: the `id` returned by `growsurf_list_campaigns`, not the program name or a share URL. Defaults to GROWSURF_CAMPAIGN_ID when omitted. Program IDs also identify newly created programs without restarting the server.
participantsYesGrowSurf participant IDs and/or email addresses to delete (1-200 entries; mixed lists allowed).

Output Schema

NameRequiredDescriptionDefault
resultsNoOne entry per submitted identifier, in request order.
summaryNoCounts across all submitted entries.
analyticsErasureNoAnalytics erasure is pending. Reports can retain removed participants until erasure completes. Do not repeat successful deletions.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.19.33
    • changedInput schema / properties / campaignId / description
      Previous 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."New value: +"Target program id for this call: the `id` returned by `growsurf_list_campaigns`, not the program name or a share URL. Defaults to GROWSURF_CAMPAIGN_ID when omitted. Program IDs also identify newly created programs without restarting the server."
  2. Changed2 schema fields changedv0.19.15
    • addedInput schema / properties / campaignId / minLength
      Added value: +1
    • changedInput schema / required
      Previous value: -[
      -  "participants"
      -]New value: +[
      +  "participants",
      +  "campaignId"
      +]
  3. Changed1 schema field changedv0.19.9
    • 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."
  4. Changed2 schema fields changedv0.15.1
    • changedOutput schema / description
      Previous value: -"Bulk delete outcome. A `200` response can still include `NOT_FOUND` or `ERROR` rows, so check the summary."New value: +"Bulk delete outcome. A `202` response includes `analyticsErasure` when analytics erasure is pending. Both `200` and `202` responses can include `NOT_FOUND` or `ERROR` rows, so check the summary."
    • addedOutput schema / properties / analyticsErasure
      Added value: +{
      +  "description": "Analytics erasure is pending. Reports can retain removed participants until erasure completes. Do not repeat successful deletions.",
      +  "properties": {
      +    "operationId": {
      +      "description": "Opaque reference for support inquiries about this analytics erasure.",
      +      "type": "string"
      +    },
      +    "status": {
      +      "description": "Erasure has been accepted but is not confirmed complete.",
      +      "enum": [
      +        "pending"
      +      ],
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
  5. First observedv0.12.2

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations (destructiveHint, idempotentHint), it discloses that deletion is permanent, that access is removed immediately while record cleanup is automatic and subject to financial retention, and that reports may still show the participant until cleanup finishes. It also explains 200 vs 202 semantics, the four row statuses, duplicate resolution, and the analyticsErasure field — behavior an agent cannot infer from annotations alone.

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 the DESTRUCTIVE warning, then details outcomes. It is dense and mostly earns its length, though the status-code enumeration is long enough that the payload-format detail could be trimmed since an output schema exists.

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 destructive bulk mutation with only two parameters, the description covers risk, limits, targeting defaults, and both sync and async response shapes. Nothing an agent needs in order to call it correctly and interpret results is missing.

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 coverage is 100%, so the baseline is 3, but the description adds real meaning: entries may mix IDs and emails, the 200-entry ceiling and chunking strategy, and that campaignId overrides the environment default. This goes beyond the schema's per-field text without contradicting 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 opens with a specific verb and resource ('Bulk delete participants from your GrowSurf program in one request') and immediately scopes it as bulk (up to 200 entries), which cleanly separates it from growsurf_bulk_move_participants and growsurf_list_participants. An agent knows exactly what operation this performs 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 Guidelines4/5

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

It gives concrete operational guidance: chunk lists larger than 200 across multiple calls, and 'Do not repeat successful rows to finish cleanup.' It also explains target resolution (campaignId vs GROWSURF_CAMPAIGN_ID). It does not explicitly contrast with sibling tools such as bulk_move or a single-participant delete, so it stops short of full when/when-not routing.

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

Deploy Server

Other Tools