List hardware tokens enrolled to a Duo user, showing type and serial without exposing secret seeds.
List the hardware tokens enrolled to a user (type, serial - never the token's secret seed, which is stripped).
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Number of items per page (Duo default/max vary by endpoint). | |
| offset | No | Offset into the result set, for paging past the first page. | |
| userId | Yes | Duo user_id. |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the behavioral disclosure burden, and it does add one valuable safety-relevant fact: the secret seed is stripped from the response. It also indicates output is limited to type and serial. However, it says nothing about pagination behavior, error cases, or authorization requirements, which would be useful for a list tool.
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?
A single sentence that front-loads the action and scope, then appends the two most decision-relevant facts (returned fields and the secret-stripping behavior) with zero filler or repetition. Every word earns its place.
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?
For a simple read-only list tool with fully documented parameters, the description covers the key facts an agent needs: what is listed, for whom, and the sensitive-data exclusion. Since there is no output schema, the lack of detail about the pagination envelope (result shape, totals) is a minor gap but does not prevent correct invocation.
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 input schema already documents all three parameters with 100% coverage, including limit and offset semantics, so the description adds little parameter-level meaning. The only added value is the implicit link between the userId parameter and the 'enrolled to a user' scoping, plus the output-field note (type, serial), which matches the baseline for high schema 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?
The description names a specific action and resource ('List the hardware tokens enrolled to a user') and clarifies the returned fields (type, serial), which clearly separates it from the global duo_list_hardware_tokens. However, it does not explicitly distinguish hardware tokens from the overlapping sibling tools duo_list_user_u2f_tokens and duo_list_user_webauthn_credentials, so an agent could be unsure which per-user token list fits its need.
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?
The phrase 'enrolled to a user' implies this is the tool to use when a specific user's hardware tokens are needed rather than the global token list, but it does not state when to choose this over the U2F or WebAuthn per-user tools, nor does it name any alternative explicitly. Usage context is inferable but not stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.