Check whether the user has approved the device authorization. Call every 5 seconds (or the interval returned by a slow_down response) until status is 'complete'. Save the returned api_token to your MCP server config.
| Name | Required | Description | Default |
|---|---|---|---|
| device_code | Yes | device_code returned by request_device_auth |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does well. It discloses the polling behavior, handling of slow_down responses, and the terminal condition ('complete'). It also mentions the api_token return, which helps the agent understand the tool's practical side effects.
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 description is two concise sentences that deliver essential information without waste. It front-loads the purpose and follows with actionable usage details.
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 one-parameter polling tool, the description fully covers the usage loop, termination condition, and output handling. No output schema exists, but the description indicates what to do with the response (save api_token). This is complete for the tool's complexity.
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 schema already fully describes the parameter (device_code returned by request_device_auth) with 100% coverage. The description does not add additional parameter-specific semantics, so the baseline of 3 is appropriate.
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 clearly states the tool's purpose: to check whether the user has approved device authorization. It uses a specific verb ('check') and resource ('device authorization'), which distinguishes it from sibling tools like request_device_auth that initiates the flow.
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 description provides explicit usage instructions: call every 5 seconds or the interval from a slow_down response until status is 'complete'. It also specifies what to do with the returned api_token (save to config), making the polling workflow clear.
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.
Each tool has a distinct role: document CRUD (create, get, update, archive), listing/searching, annotation create/list, and two auth helper tools. There is no overlap or ambiguity between them.
All tools follow a consistent verb_noun pattern with snake_case (e.g., create_document, list_annotations, request_device_auth). The naming is uniform and predictable across both document and auth tools.
With 10 tools, the server is well-scoped for document management plus required auth flow. It covers the essential operations without being bloated or too thin.
Core document operations are covered (create, read, update, archive, list, search), but there is no hard delete or unarchive, and annotations only support create/list (no update/delete). Additionally, there is no explicit tool for sharing documents despite the mention of shared docs.
