twelvebit Analytics

Revoke an API key

revoke_api_key

DestructiveIdempotent

Revoke a site key, so every request with it fails at once. Get the id from list_api_keys. Needs confirm: true; without it the tool only shows what it would revoke. Check with the user first: scripts and agents that use the key stop working. New keys are made in the dashboard, so no secret passes through the chat.

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": {
      "key_id": "<key_id>"
    },
    "name": "revoke_api_key"
  }
}

Input Schema

Name	Required	Description
`site`	No	Site domain (example.com), id or public id (tb_…). Optional with a site key, or when the account has one site.
`key_id`	Yes
`confirm`	No	Set to true to really do it. Without it, the tool only describes what it would do.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already declare destructiveHint=true and idempotentHint=true, yet the description adds material context beyond them: breakage is immediate and total for anything using the key, and omitting confirm turns the call into a non-mutating preview. That dry-run behavior is not derivable from the annotations and is the key thing an agent needs.

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?

Five short sentences, front-loaded with the effect and the prerequisite before the safety warning. The closing point about the dashboard is slightly tangential to revocation but earns its place by telling the agent where recovery happens.

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?

No output schema exists, so the description carries the return burden, and it does: without confirm it 'only shows what it would revoke'. Combined with the safety warning and recovery path, an agent has everything needed to invoke this correctly and responsibly.

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 67%, and key_id has no schema description at all, which the description compensates for by telling the agent to source it from list_api_keys. The confirm dry-run semantics are reinforced, though the optional 'site' parameter is left entirely to the schema and the id format (40-char max) is not restated.

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 ('Revoke a site key') plus the immediate effect ('every request with it fails at once'), which separates it from roll_api_key and delete_* siblings. An agent knows exactly which operation this is without opening the 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 the prerequisite step (get the id from list_api_keys), the required flag (confirm: true), and the human-in-the-loop requirement ('Check with the user first') with the reason (scripts and agents stop working). It also redirects key creation to the dashboard, so the agent knows what this tool is not for.

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

All twelvebit Analytics tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?