Create a full-access catalog/inventory API key. Requires OAuth security:write.
The secret is returned ONCE. Store it securely; never include it in a public
message or logs. This grants broader catalog/inventory access than a limited
OAuth token. It cannot manage account settings or credentials through MCP.
Each call creates a new key; do not retry blindly after a lost response.
| Name | Required | Description | Default |
|---|---|---|---|
| label | No |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Above the annotation bar by a wide margin: annotations only declare readOnly=false/destructive=false, while the description adds the required OAuth scope, the one-time-visible secret and its storage obligation, and effective non-idempotency ('each call creates a new key; do not retry blindly'). These are exactly the facts that change how an agent behaves after a failed call, and none are recoverable from structured fields.
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?
Roughly five short sentences, front-loaded with the action and the auth requirement, then the irreversible consequence, then the scope comparison. No filler and no repetition of the tool name or annotations.
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 and thin annotations, the description carries the operational burden well: secret visibility, scope, and retry hazard are all covered. The remaining gap is the undocumented 'label' argument, which an agent must guess at.
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?
The single parameter 'label' has 0% schema description coverage and the description never mentions it — no format, no purpose, no default behavior. It does not compensate for the coverage gap; only the self-evident name carries the agent, which is below the 'must compensate' bar for low coverage.
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 with its exact scope: 'Create a full-access catalog/inventory API key.' It further distinguishes this credential from the broader/limited alternatives ('grants broader catalog/inventory access than a limited OAuth token') and its boundary ('cannot manage account settings or credentials through MCP'), so an agent knows precisely what class of principal it is minting.
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 a hard precondition ('Requires OAuth security:write') and an explicit when-not-to ('do not retry blindly after a lost response' after a lost response). It does not name the sibling operations it competes with (revoke_account_api_key, rotate_account_api_key, list_account_api_keys), but the create-vs-other distinction is unambiguous from the verb.
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.