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

Annotations already declare readOnly=false, destructive=true and openWorld=true, so the safety profile is carried by structured data. The description adds non-obvious behavioral value: which returned values are user-facing and which must be kept secret, plus the handoff to the poll tool. It does not explain that this initiates server-side session state, so it stops short of a 5.

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 short, front-loaded sentences with no filler; the core action comes first and the secret-handling rule is stated explicitly rather than implied.

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 helpfully enumerates the return fields an agent must act on and the handoff tool. It omits failure modes, code expiry, or that a session is created, which would round out an auth-flow starter, but the essential calling information is present.

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?

Zero parameters, so the schema has nothing to document and the baseline is 4. The description goes further by naming the three return fields (verification_uri, user_code, poll_secret) and their handling, which is useful since no output schema exists.

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 ('Starts Google device login') that clearly separates it from the sibling 'dex_auth_gate_login_start' and names the continuation tool 'dex_auth_google_login_poll'. An agent can identify the tool and its place in the flow without opening any 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?

Provides a clear protocol: show verification_uri and user_code to the user, keep poll_secret for the poll tool, and never display it. This routes the agent to the correct follow-up tool, though it gives no explicit exclusion against the gate-login variant or error/expiry conditions.

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