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

ghl-mcp-server-v2

by zackscriven

ghl_kb_crawler_delete_urls

DestructiveIdempotent

Removes trained website pages from a knowledge base so the AI no longer references them. Deletes specific URLs or bulk-deletes filtered/all crawled pages.

Instructions

Delete trained pages Removes trained website pages from a knowledge base so the AI no longer references them. WHEN TO USE: use this when you need to drop specific or all trained URLs; use trainDiscoveredUrls to add pages; use getAllWebsiteUrlsDataByKnowledgeBase to list what is trained. RETURNS: whether the delete succeeded. Endpoint: DELETE /knowledge-bases/crawler (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_crawler_delete_urls"
  }
}

Input Schema

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

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed11 schema fields changedv2.1.0
    • addedInput schema / properties / body / properties / deleteAll
      Added value: +{
      +  "description": "delete all flag",
      +  "example": false,
      +  "type": "boolean"
      +}
    • addedInput schema / properties / body / properties / excludeUrlIds
      Added value: +{
      +  "description": "URL IDs to exclude from a deleteAll operation (select-all-minus-some flow)",
      +  "example": [
      +    "689268c7a64d801ef7bb44aa"
      +  ],
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • changedInput schema / properties / body / properties / knowledgeBaseId / description
      Previous value: -"knowledge base ID as string"New value: +"Knowledge base ID as string (optional)"
    • changedInput schema / properties / body / properties / knowledgeBaseId / example
      Previous value: -"tDtDnQdgm2LXpyiqYvZ6"New value: +"I1rITlYLJofFosIqC4Np"
    • changedInput schema / properties / body / properties / locationId / description
      Previous value: -"location ID as string"New value: +"Location ID as string"
    • changedInput schema / properties / body / properties / locationId / example
      Previous value: -"tDtDnQdgm2LXpyiqYvZ6"New value: +"qIyivCmsuEOSnyoFYEej"
    • addedInput schema / properties / body / properties / search
      Added value: +{
      +  "description": "Substring filter (case-insensitive) matched against `url` or `title` to scope deleteAll to filtered rows only. Mirrors the search semantics of the list endpoint.",
      +  "example": "blog",
      +  "type": "string"
      +}
    • changedInput schema / properties / body / properties / urlIds / description
      Previous value: -"List of trained urls ids ( fetched from the Get all trained page links by knowledge base endpoint)"New value: +"List of URL ids"
    • changedInput schema / properties / body / properties / urlIds / example
      Previous value: -"[tDtDnQdgm2LXpyiqYvZ6]"New value: +[
      +  "689268c7a64d801ef7bb44aa"
      +]
    • changedInput schema / properties / body / required
      Previous value: -[
      -  "knowledgeBaseId",
      -  "locationId",
      -  "urlIds"
      -]New value: +[
      +  "locationId",
      +  "urlIds",
      +  "deleteAll"
      +]
    • addedInput schema / properties / body / title
      Added value: +"BulkDeleteUrlsRequestBodyDTO"
  2. First observedv2.0.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already carry destructiveHint=true, idempotentHint=true and openWorldHint=true, so the safety profile is covered. The description adds genuinely non-structured context: the endpoint, the required Sub-Account (location) token, the knowledge-bases.write OAuth scope, and the fact that it returns a success flag. It stops short of saying explicitly that deletion is irreversible or how deleteAll interacts with excludeUrlIds in failure cases.

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 verb and consequence, then WHEN TO USE, RETURNS, endpoint and scope metadata in clearly labeled blocks. The only redundancy is the title-like first line 'Delete trained pages' immediately echoed by 'Removes trained website pages...', which is minor waste.

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?

No output schema exists, and the description compensates with 'RETURNS: whether the delete succeeded.' Auth prerequisites and the endpoint are disclosed, and the nested request body is fully specified in the schema. What's missing is a note on the interaction between deleteAll, search and excludeUrlIds at the behavioral level, which matters for a destructive bulk operation.

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% and every body property (search, urlIds, deleteAll, locationId, excludeUrlIds, knowledgeBaseId) is documented inline, so the baseline is 3. The description adds framing beyond the schema by distinguishing the two deletion modes ('specific or all trained URLs'), which tells the agent that deleteAll and urlIds are mutually exclusive intents.

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 and resource ('Delete trained pages', 'Removes trained website pages from a knowledge base') and adds the downstream consequence ('so the AI no longer references them'). It is immediately distinguishable from the neighboring crawler tools (train, list_urls, status, discover).

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?

An explicit WHEN TO USE block names the condition for this tool ('drop specific or all trained URLs') and routes to alternatives by name: trainDiscoveredUrls to add pages, getAllWebsiteUrlsDataByKnowledgeBase to inspect what is trained. The names map cleanly onto siblings ghl_kb_crawler_train and ghl_kb_crawler_list_urls.

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