Skip to main content
Glama

Delete Keyword

delete_keyword
DestructiveIdempotent

Permanently delete a keyword and all its mentions when you need to remove it from monitoring and free an active plan slot; this cannot be undone.

Instructions

Permanently delete one keyword in any status, together with every mention it produced. There is no undo and no restore: disable_keyword pauses a keyword and keeps its mentions, edit_keyword fixes a SUSPENDED value, and delete_website drops a whole site. Deleting an active keyword frees a plan slot, so the oldest pending keyword that now fits the plan may become active, which queues public-network searches and ranking checks; this tool does not issue a refund or change the subscription. Confirm with the user first and name the keyword, not just the ID. Returns { deleted: true }; 404 if the ID is unknown to this account.

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": {
      "keywordId": "<keywordId>"
    },
    "name": "delete_keyword"
  }
}

Input Schema

NameRequiredDescriptionDefault
keywordIdYesID of the keyword to erase, from the keywords list in list_websites or get_website
workspaceIdNoWorkspace to act in: an id from list_workspaces. Omit to use the default workspace. Use the same workspaceId for every call about the same workspace, since ids from one workspace do not exist in another

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed11 schema fields changedv1.6.0
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
    • changedInput schema / properties / keywordId / description
      Previous value: -"Keyword ID (UUID)"New value: +"ID of the keyword to erase, from the keywords list in list_websites or get_website"
    • addedInput schema / properties / keywordId / format
      Added value: +"uuid"
    • addedInput schema / properties / workspaceId
      Added value: +{
      +  "description": "Workspace to act in: an id from list_workspaces. Omit to use the default workspace. Use the same workspaceId for every call about the same workspace, since ids from one workspace do not exist in another",
      +  "type": "string"
      +}
    • removedOutput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
    • addedOutput schema / properties / result / additionalProperties
      Added value: +true
    • removedOutput schema / properties / result / description
      Removed value: -"{ deleted: true } once the PENDING keyword is removed."
    • addedOutput schema / properties / result / properties
      Added value: +{
      +  "deleted": {
      +    "description": "Always true on success; a failed delete returns an error instead",
      +    "type": "boolean"
      +  }
      +}
    • addedOutput schema / properties / result / required
      Added value: +[
      +  "deleted"
      +]
    • addedOutput schema / properties / result / type
      Added value: +"object"
    • addedOutput schema / required
      Added value: +[
      +  "result"
      +]
  2. Changed1 schema field changedv0.1.1
    • changedOutput schema / properties / result / description
      Previous value: -"Confirmation that the keyword was deleted."New value: +"{ deleted: true } once the PENDING keyword is removed."
  3. First observedv0.1.0

TDQS

A4.4/5.0
Behavior3/5

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

Annotations already declare destructiveHint, openWorldHint and idempotentHint, so the safety profile is known; the description still adds real value with 'no undo and no restore', cascade deletion of mentions, and the plan-slot side effect that can activate the oldest pending keyword and queue searches. It also states no refund or subscription change occurs and documents the 404 case. The one redundant piece is 'Returns { deleted: true }', which the output schema already covers, so it falls short of a 5.

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 destructive action and its irreversibility, then alternatives, then side effects, then the confirmation rule. Every sentence carries information, though the plan-slot sentence is dense enough that it takes a second read.

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 cascade delete with only two parameters, the definition covers irreversibility, cascade scope, downstream side effects, billing non-effects, error behavior and a human-confirmation requirement. Nothing an agent needs to call it safely 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 account-scoping meaning ('404 if the ID is unknown to this account') and a usage rule that the keyword should be named to the user rather than passed as a bare ID. Workspace semantics are left entirely to the 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?

States a specific verb and resource ('Permanently delete one keyword'), adds scope ('in any status, together with every mention it produced'), and explicitly separates it from disable_keyword, edit_keyword and delete_website. An agent can distinguish it from every sibling without opening a 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?

Names three concrete alternatives and the condition each serves (disable pauses and keeps mentions, edit fixes a SUSPENDED value, delete_website drops a site). It also gives a procedural rule: confirm with the user first and name the keyword rather than just the ID.

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