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

ghl-mcp-server-v2

by zackscriven

ghl_kb_create_knowledge_base

Create a new knowledge base for a location by providing a name and optional description, adding a knowledge source with a server-assigned ID (max 15 per location).

Instructions

Create a new knowledge base (max 15 knowledge bases per location) Creates a new knowledge base for a location (maximum 15 per location). WHEN TO USE: use this when you need to add a brand-new knowledge source; use updateKnowledgeBase to rename one; use create (FAQs) or trainDiscoveredUrls to add content. RETURNS: success and the created knowledge base, including its server-assigned id. Endpoint: POST /knowledge-bases/ (Version header: v3; source: v3/knowledge-base-v3.json) Requires a Sub-Account (location) token. OAuth scopes: knowledge-bases.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_kb_create_knowledge_base"
  }
}

Input Schema

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

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv2.1.0
    • addedInput schema / properties / body / properties / description / description
      Added value: +"Optional description of the knowledge base"
    • addedInput schema / properties / body / properties / description / example
      Added value: +"A knowledge base for customer support FAQs"
    • addedInput schema / properties / body / properties / locationId / description
      Added value: +"The location ID this knowledge base belongs to"
    • addedInput schema / properties / body / properties / locationId / example
      Added value: +"qIyivCmsuEOSnyoFYEej"
    • addedInput schema / properties / body / properties / name / description
      Added value: +"Name of the knowledge base"
    • addedInput schema / properties / body / properties / name / example
      Added value: +"My Knowledge Base"
    • addedInput schema / properties / body / title
      Added value: +"CreateKnowledgeBaseDTO"
  2. First observedv2.0.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false, openWorldHint=true). The description adds genuinely new context: the 15-per-location cap, the required Sub-Account token, and the OAuth scope knowledge-bases.write. It does not restate the write/non-idempotent nature already implied by annotations, though it also does not explain what happens on hitting the cap.

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?

Well front-loaded with labeled WHEN TO USE and RETURNS sections, and the endpoint/auth metadata is easy to scan. It loses a point because the opening clause and the first sentence restate the same fact ('max 15 knowledge bases per location'), and the alternative names use camelCase identifiers (updateKnowledgeBase, trainDiscoveredUrls) that don't literally match the ghl_kb_* sibling names.

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 mutation tool with a nested body and no output schema, the description supplies everything the agent needs: the return shape (created KB with server-assigned id), auth requirements, endpoint, scope, and quota. Nothing material is missing for correct invocation.

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% (name, locationId, description all documented with examples), so the schema carries parameter semantics. The description adds only the implicit location scoping and does not explain that locationId must match the token's sub-account, which is the one non-obvious constraint on this body.

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+resource ('Create a new knowledge base') with an explicit scope constraint (max 15 per location), and names the siblings it is not (updateKnowledgeBase, FAQ create, trainDiscoveredUrls). An agent can distinguish it from ghl_kb_update_knowledge_base and ghl_kb_faq_create without opening any schema.

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?

The WHEN TO USE block gives both the positive trigger ('add a brand-new knowledge source') and route-outs to renaming (updateKnowledgeBase) and content-adding (FAQs, discovered URLs). This is explicit when/when-not with named alternatives, not implied usage.

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