Poll Google device login; returns pending/ok/error. Requires poll_secret from start. [write] On ok: immediately replace stored mcp_token with login_result.mcp_token — new token is tied to a different account.
| Name | Required | Description | Default |
|---|---|---|---|
| flow_id | Yes | Flow ID returned by dex_auth_google_login_start | |
| poll_secret | Yes | One-time poll secret returned by dex_auth_google_login_start. Do not show this value to the user. |
Changes observed during successful MCP inspections.
Input schema / properties / poll_secretAdded value: +{
+ "description": "One-time poll secret returned by dex_auth_google_login_start. Do not show this value to the user.",
+ "type": "string"
+}Input schema / requiredPrevious value: -[
- "flow_id"
-]New value: +[
+ "flow_id",
+ "poll_secret"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already flag destructive=true and readOnly=false, and the description goes further with the critical operational instruction to replace the stored mcp_token on 'ok', warning that the new token belongs to a different account. That is exactly the kind of consequence an agent cannot infer 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?
Two sentences, front-loaded: the status-returning behavior first, then the credential requirement, then the post-success instruction. Every clause carries information, including the [write] marker signaling mutation.
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 compensates by naming the return states (pending/ok/error) and the post-success token-swap obligation. Nothing an agent needs to invoke it correctly or act on its result is missing.
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 100%, so both parameters are already documented in the schema, including the one-time nature of poll_secret. The description's 'Requires poll_secret from start' restates rather than extends that, so baseline 3 applies.
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 ('Poll Google device login') plus its return states ('pending/ok/error'), and implicitly distinguishes itself from the sibling dex_auth_google_login_start that produces the credentials it consumes. An agent can tell exactly what this tool does without opening the 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?
It names the prerequisite ('Requires poll_secret from start'), which routes the agent to the correct upstream tool. It does not state polling cadence, termination conditions, or what to do on 'error', but the usage context is otherwise 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.