Replace an API key's secret immediately, invalidating the old secret. This irreversible action requires explicit user confirmation and the api_keys:write scope.
Replace the key's secret (the old secret stops working immediately).
DESTRUCTIVE: this cannot be undone. Only call it when the user explicitly asked for exactly this action.
Requires scope api_keys:write.
DESTRUCTIVE: cannot be undone.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes |
Changes observed during successful MCP inspections.
v0.1.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true and idempotentHint=false, so the safety bar is lower, yet the description adds real value: the old secret stops working immediately and the call requires scope `api_keys:write`. The duplicated "DESTRUCTIVE: cannot be undone" lines restate what annotations already say, adding no new information.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The core sentence and scope requirement are front-loaded and efficient, but the destructive warning is stated twice in near-identical wording, which wastes space without adding information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Risk, scope requirement, and the effect on the old secret are all covered, which is solid for a destructive mutation. However, there is no output schema and the description does not say whether the new secret is returned in the response — critical for a rotation tool the agent may need to surface to the user — nor does it clarify the `id` parameter.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% and the single parameter `id` is never mentioned in the description. The agent is told what the tool does but not that it must supply the API key's identifier, leaving a real gap for a one-parameter mutation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ("Replace the key's secret") plus the immediate consequence, so the agent can distinguish it from create_api_key and revoke_api_key. It does not explicitly contrast with the near-identical sibling rotate_webhook_secret, which would have made the differentiation airtight.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
"Only call it when the user explicitly asked for exactly this action" is an explicit when-to-use guardrail, and the destructive framing makes the exclusion clear. It stops short of 5 because it never names the alternative paths (revoke_api_key, create_api_key) an agent might confuse it with.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.