Skip to main content
Glama
ghl-mcp-server-v2

ghl-mcp-server-v2

by zackscriven

ghl_opportunity_upsert

Create or update a GoHighLevel opportunity in one call, setting pipeline stage, status, value, and followers.

Instructions

Upsert Opportunity Endpoint: POST /opportunities/upsert (Version header: v3; source: v3/opportunities-v3.json) OAuth scopes: opportunities.write

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": {
      "body": "<body>"
    },
    "name": "ghl_opportunity_upsert"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYesRequest body (schema carried verbatim from the official OpenAPI spec).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv2.1.0
    • changedInput schema / properties / body / properties / monetaryValue / description
      Previous value: -"Monetary value of the opportunity"New value: +"Monetary value of the opportunity, e.g. 220. (Spec bug override 2026-08-27: upstream declares this as an empty object schema with a numeric example, which rejected every numeric value client-side.)"
    • removedInput schema / properties / body / properties / monetaryValue / example
      Removed value: -220
    • changedInput schema / properties / body / properties / monetaryValue / type
      Previous value: -"object"New value: +"number"
    • addedInput schema / properties / body / title
      Added value: +"UpsertOpportunityDto"
  2. First observedv2.0.0

TDQS

C2.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=true; the description adds the OAuth scope (opportunities.write) and API version header, which is genuine extra context. However it omits the key behavioral fact for an upsert: whether an omitted `id` creates a duplicate, and how the required followers/isRemoveAllFollowers/followersActionType fields behave on update. Note the mild tension between "upsert" and idempotentHint=false that the description does not resolve.

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?

Three short, front-loaded lines with no filler; the endpoint, spec version and scope are compactly stated. Some of that (source file path, v3 header note) is metadata noise for an agent caller rather than decision-relevant content.

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

Completeness2/5

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

This is a mutation with a nested body, five required sub-fields (including non-obvious follower flags), no output schema and no explanation of what a successful response contains or which object is returned. For that complexity, a name restatement plus scope is not enough to call it correctly with confidence.

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 nested UpsertOpportunityDto documents every property with examples, enums and format notes, so the description adds nothing beyond it. Baseline 3 for full schema coverage applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Upsert Opportunity" plus the endpoint path restates the tool name and adds an HTTP verb/path; it never explains what upsert means here (which key determines create-vs-update, e.g. whether supplying `id` updates and omitting it creates). With siblings ghl_opportunity_create and ghl_opportunity_update present, there is no differentiation at all, leaving an agent unable to choose between the three.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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

No when-to-use guidance, no exclusions, no mention of the create/update siblings it overlaps with. The only operational hint is the OAuth scope, which is a prerequisite rather than a usage rule.

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