Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The tool is a polling operation, and the description says 'Poll for device login completion' and notes that success returns a sessionKey. This adds context beyond the annotations, which only state readOnlyHint=false, idempotentHint=false, and destructiveHint=false. It doesn't detail error behavior or what happens before completion, but for a simple poll the disclosure is adequate.

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?

Three sentences, each earning its place: purpose, call sequence, and required input/return handling. The most important information is front-loaded, and there is no filler or repetition.

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 one-parameter tool with a clear position in a flow, the description covers the prerequisite call, input origin, success return, and how to use the result. It doesn't mention failure modes or polling behavior details, but an output schema exists and the sibling list clarifies the flow context, so the omission is minor.

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 coverage is 100%: the parameter deviceCode is already described as 'The device_code value returned by loginWithDevice.' The description repeats this ('the device_code returned by loginWithDevice') and adds 'Required,' but this is also already in the schema's required list. No new semantic information about the parameter is provided beyond the schema.

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 opens with 'Poll for device login completion,' which names a specific verb and resource, clearly distinguishing this tool from its siblings like loginWithDevice (which initiates the flow) and getAuthStatus (which checks general auth state). It also states the concrete success outcome ('returns a sessionKey'), leaving no ambiguity about what the tool does.

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 explicitly gives the usage context: 'Call this after loginWithDevice() once you have opened the verification URL and signed in.' It also specifies the prerequisite input (deviceCode returned by loginWithDevice) and the downstream behavior ('pass it as the sessionKey argument on every subsequent authenticated tool call'), making the call sequence unambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.