Skip to main content
Glama
GrowSurf MCP Server

GrowSurf MCP Server

Official

Troubleshoot Referral Tracking

growsurf_troubleshoot_referral_tracking
Read-onlyIdempotent

Diagnoses referral tracking problems from a symptom or description and returns ordered checks, likely causes, fixes, and documentation links.

Instructions

Diagnose referral tracking and program problems. Accepts a symptom or description without requiring a program or participant ID. Covers referrals not credited, participant emails not sending, rewards not issued, participants not added, Universal Code not detected, integrations or CRMs not syncing, Zapier errors, fraud flags, and analytics discrepancies. Returns ordered diagnostic checks, likely causes, fixes, and documentation links. It does not read program or participant records. Unknown symptom keys return the available symptoms. A description matches only when it contains a symptom label or alias verbatim; otherwise the symptom list is returned.

Input Schema

NameRequiredDescriptionDefault
symptomNoThe symptom to diagnose. Known keys: `participant_emails_not_sending`, `reward_not_issued`, `referral_not_credited`, `participants_not_added`, `universal_code_not_detected`, `platform_specific_install`, `numbers_do_not_match`. Unknown keys return the symptom list.
campaignIdNoTarget 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.
descriptionNoThe problem in the customer's words, when `symptom` is unknown.
participantIdNoAffected participant id, echoed into participant-level checks.
participantEmailNoAffected participant email, when the id is unknown.

Output Schema

NameRequiredDescriptionDefault
markdownNoThe generated guidance as a markdown document.

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. 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."
  3. Addedv0.14.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare this as a read-only, idempotent, closed-world operation, so the safety profile is covered. The description goes further by describing the return shape (ordered diagnostic checks, likely causes, fixes, documentation links) and two failure modes — unknown symptom keys returning the symptom list, and description text that fails to match unless it contains a label verbatim. What it does not address is the response when partial filters are supplied.

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?

It is front-loaded with purpose, then scope, then symptom coverage, then return behavior, then edge cases — a logical order with no filler sentences. It is dense and slightly long for a lookup-style tool, but each sentence carries distinct information.

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

Completeness4/5

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

With an output schema present and full parameter coverage, the description only needs to carry purpose, routing, and edge-case behavior, which it largely does. The one gap is that it never explains how the optional campaignId/participantId context changes the diagnostic output, which matters given all five parameters are optional.

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

Parameters3/5

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

Schema description coverage is 100% and the schema already documents the known symptom keys, the campaignId default, and the purpose of participantId/participantEmail, so the baseline is 3. The description adds real value only for the `description` parameter by disclosing the verbatim-match rule, but that is a narrow addition over a fully documented schema.

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 ('Diagnose referral tracking and program problems') and explicitly bounds scope with 'It does not read program or participant records', which separates it from data-retrieval siblings like get_campaign or get_participant. It also enumerates the concrete symptom families it handles, so an agent can match a user complaint to this tool 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 states the entry conditions clearly ('Accepts a symptom or description without requiring a program or participant ID') and lists the problem classes that qualify, which is strong when-to-use guidance. The negative case is implied rather than named — it says it does not read records but does not point at the specific retrieval siblings to use instead.

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