Create a replacement for your key, keeping the old key ACTIVE. Requires OAuth security:write.
Returns the replacement secret ONCE with its new ID. Install it in the
consumer, test it, then call revoke_account_api_key with previous_key_id.
Do not revoke until the replacement is working. Each call creates a key;
do not retry blindly after a lost response. Never publish the secret.
| Name | Required | Description | Default |
|---|---|---|---|
| key_id | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Goes well past the annotations: it discloses the required OAuth scope (security:write), that the secret is returned only ONCE, that each call creates a new key (non-idempotent), and the handling constraint on the secret. Annotations only cover the generic safety flags, so this added context is substantial.
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?
Front-loaded with the purpose and scope, then proceeds through auth, return behavior, and the follow-up workflow. Every sentence carries actionable information; nothing is padding.
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?
With no output schema, the description still explains the return value (the secret once, with its new ID), auth requirements, non-idempotency, and the required follow-up call. An agent has everything needed to sequence and call this tool safely.
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% for the single key_id parameter, so the schema supplies only 'Key Id' (integer). The description never explains that key_id is the key being rotated; instead it introduces previous_key_id, which is a parameter of a different tool, potentially conflating the two. It does not compensate for the coverage gap.
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 ('Create a replacement for your key') plus the crucial scope distinction that the old key stays ACTIVE. This separates it cleanly from both create_account_api_key and revoke_account_api_key without needing to open any schema.
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?
Gives an explicit ordered workflow: install the replacement, test it, then call revoke_account_api_key with previous_key_id. It also names the when-not condition ('Do not revoke until the replacement is working') and warns against blind retries after a lost response.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.