Skip to main content
Glama

Destroy a website, app, agent, or skill

destroy_service
DestructiveIdempotent

Permanently destroy a website, app, agent, or skill. This cannot be undone, so confirm with the user first. Destroying a website or app stops serving it. Destroying an app stops it and removes its releases and source; its resources are detached and kept, because they belong to the organization and may serve other apps, and the answer names them for destroy_resource. Destroying an agent stops it and removes its channels, agent-scoped connectors, drains, mailboxes, releases, and source repository; none of those can be recovered. Its sessions and memories remain, and once the agent is gone no MCP tool can remove them (list_sessions and list_memories find them, paging with cursor), so call destroy_session and destroy_memory first if they should go. The architect agent cannot be destroyed. Destroying a skill removes it from list_skills and frees its name; it is refused while any agent has the skill attached, and the refusal names detach_skill, which frees each one. Destroying a skill under a well-known name, such as governance or design-system, brings back Valet's default for every agent in the organization. A name that no longer exists answers that nothing was destroyed. Identify the service by name, which requires connecting a Valet 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": {
      "name": "<name>"
    },
    "name": "destroy_service"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoThe kind you believe the named service is, as a safeguard against destroying the wrong thing. Omit to destroy whatever the name holds.
nameYesThe website's, app's, agent's, or skill's name to destroy.
org_nameNoThe Valet organization it belongs to. Omit to use the organization the account joined first.

Output Schema

NameRequiredDescriptionDefault
orgYesName of the Valet organization the call acted in.
urlNoAddress that has stopped serving, read before the takedown. Absent for a skill, a service that had no address, an agent in an organization whose agent URLs are not turned on, and when already_gone is true.
kindYesKind destroyed: site, app, agent, or skill. When already_gone is true, the kind passed in the call, or service if none was passed.
nameYesName of the service that was destroyed, or that was already gone.
already_goneNoTrue when no service held the name before the call, so nothing was destroyed. A repeat of a destroy returns this. Absent otherwise.
restored_defaultNoTrue when the destroyed skill replaced a built-in skill, so Valet's default answers under its name again for every agent in the organization. Absent otherwise.
detached_resourcesNoNames of the resources an app's takedown detached. Each still exists with its data; pass a name to destroy_resource to delete it. Absent for other kinds and for an app with none.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / kind / description
      Previous value: -"The kind you expect the name to hold. A guard against destroying the wrong thing: a name that holds another kind is refused and nothing is destroyed. Omit to destroy whatever the name holds."New value: +"The kind you believe the named service is, as a safeguard against destroying the wrong thing. Omit to destroy whatever the name holds."
  2. Changed1 schema field changed
    • changedInput schema / properties / kind / description
      Previous value: -"The kind you mean to destroy, as a guard: a name that holds another kind is refused and nothing is destroyed. Omit to destroy whatever the name holds."New value: +"The kind you expect the name to hold. A guard against destroying the wrong thing: a name that holds another kind is refused and nothing is destroyed. Omit to destroy whatever the name holds."
  3. Changed1 schema field changed
    • changedOutput schema / properties / url / description
      Previous value: -"Address that has stopped serving, read before the takedown. Absent for an agent, a skill, a service that had no address, and when already_gone is true."New value: +"Address that has stopped serving, read before the takedown. Absent for a skill, a service that had no address, an agent in an organization whose agent URLs are not turned on, and when already_gone is true."
  4. Changed1 schema field changed
    • changedInput schema / properties / kind / description
      Previous value: -"The kind you mean. Omit to destroy whatever the name holds; give it to have a name holding another kind refused."New value: +"The kind you mean to destroy, as a guard: a name that holds another kind is refused and nothing is destroyed. Omit to destroy whatever the name holds."
  5. Changed8 schema fields changed
    • changedInput schema / properties / name / description
      Previous value: -"Required. The website's, app's, agent's, or skill's name, which requires a connected Valet account."New value: +"The website's, app's, agent's, or skill's name to destroy."
    • addedOutput schema / properties / already_gone / description
      Added value: +"True when no service held the name before the call, so nothing was destroyed. A repeat of a destroy returns this. Absent otherwise."
    • addedOutput schema / properties / detached_resources / description
      Added value: +"Names of the resources an app's takedown detached. Each still exists with its data; pass a name to destroy_resource to delete it. Absent for other kinds and for an app with none."
    • addedOutput schema / properties / kind / description
      Added value: +"Kind destroyed: site, app, agent, or skill. When already_gone is true, the kind passed in the call, or service if none was passed."
    • addedOutput schema / properties / name / description
      Added value: +"Name of the service that was destroyed, or that was already gone."
    • addedOutput schema / properties / org / description
      Added value: +"Name of the Valet organization the call acted in."
    • addedOutput schema / properties / restored_default / description
      Added value: +"True when the destroyed skill replaced a built-in skill, so Valet's default answers under its name again for every agent in the organization. Absent otherwise."
    • addedOutput schema / properties / url / description
      Added value: +"Address that has stopped serving, read before the takedown. Absent for an agent, a skill, a service that had no address, and when already_gone is true."
  6. Changed4 schema fields changed
    • removedInput schema / anyOf
      Removed value: -[
      -  {
      -    "required": [
      -      "name"
      -    ]
      -  },
      -  {
      -    "required": [
      -      "site_token"
      -    ]
      -  }
      -]
    • changedInput schema / properties / name / description
      Previous value: -"Give this or site_token. The website's, app's, agent's, or skill's name, which requires a connected Valet account."New value: +"Required. The website's, app's, agent's, or skill's name, which requires a connected Valet account."
    • removedInput schema / properties / site_token
      Removed value: -{
      -  "description": "Give this or name. The token returned when a website was published anonymously; it identifies that one site.",
      -  "type": "string"
      -}
    • addedInput schema / required
      Added value: +[
      +  "name"
      +]
  7. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "additionalProperties": false,
      +  "properties": {
      +    "already_gone": {
      +      "type": "boolean"
      +    },
      +    "detached_resources": {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": [
      +        "null",
      +        "array"
      +      ]
      +    },
      +    "kind": {
      +      "type": "string"
      +    },
      +    "name": {
      +      "type": "string"
      +    },
      +    "org": {
      +      "type": "string"
      +    },
      +    "restored_default": {
      +      "type": "boolean"
      +    },
      +    "url": {
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "org",
      +    "name",
      +    "kind"
      +  ],
      +  "type": "object"
      +}
  8. Changed2 schema fields changed
    • changedInput schema / properties / kind / enum
      Previous value: -[
      -  "site",
      -  "app",
      -  "agent"
      -]New value: +[
      +  "site",
      +  "app",
      +  "agent",
      +  "skill"
      +]
    • changedInput schema / properties / name / description
      Previous value: -"Give this or site_token. The website's, app's, or agent's name, which requires a connected Valet account."New value: +"Give this or site_token. The website's, app's, agent's, or skill's name, which requires a connected Valet account."
  9. Added

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true, idempotentHint=true, and openWorldHint=false, so the safety profile is supplied; the description still adds substantial context beyond that: exactly what is removed per kind (releases, source repo, channels, drains, mailboxes), what is deliberately kept (resources detached and named for destroy_resource, sessions and memories which become unreachable by any MCP tool), and the org-wide side effect of destroying a well-known skill name. It stops short only of describing the response payload, which the output schema covers.

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-loads purpose and the irreversibility warning before per-kind detail, and every sentence carries distinct behavioral information with no filler. The agent paragraph is a long run-on that could be split, but no content is wasted.

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 multi-kind tool, the definition covers consequences, irreversibility, ordering of prerequisite destroys, refusal conditions, and auth requirements; return values are handled by the existing output schema. Nothing an agent needs in order 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.

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 explains kind as a safeguard, the name, and the org_name default. The description adds only "Identify the service by name, which requires connecting a Valet account" — real but marginal value over the structured fields, so the baseline 3 fits.

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?

Opens with a specific verb and resource ("Permanently destroy a website, app, agent, or skill") and immediately disambiguates the four kinds it accepts. An agent can distinguish this from sibling tools like destroy_resource, destroy_channel, or detach_skill 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?

Explicitly states when-to-use preconditions (confirm with the user first) and routes to alternatives with conditions: call destroy_session and destroy_memory before destroying an agent, and detach_skill when a skill destroy is refused. It also names exclusions — the architect agent cannot be destroyed, and missing names return "nothing was destroyed".

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources