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

Beyond the readOnlyHint and idempotentHint annotations, the description discloses important behavioral details: it returns authorization_pending until approved, binds the session to the chosen character, and lists possible statuses with their meanings. This adds significant context about side effects and response semantics.

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 a bit long and parenthetical, but every sentence adds value—main purpose, polling guidance, and status handling. It is front-loaded with the core function and remains readable despite the density.

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?

Given there is no output schema, the description thoroughly covers expected statuses and corresponding actions, plus mentions the interval field. This is sufficient for an agent to poll effectively without guessing about return values or error handling.

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 device_code as 'The device_code returned by login_link' (100% coverage). The description reinforces this by instructing to use that code, and adds the useful note about an interval field for polling frequency, which goes slightly 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 clearly states the tool's function: 'Poll a device login started with login_link.' It uses a specific verb (poll) and resource (device login), and distinguishes itself from sibling tools like login_link (which initiates) and login (direct login).

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 gives explicit instructions: poll every few seconds, use the device_code from login_link, and how to handle each status (keep polling for authorization_pending, call login_link again for expired_token). This directly tells the agent when and how to use the tool versus alternatives.

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