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

With no annotations, the description carries the full burden. It discloses the tool returns per-step flags (terms_accepted, email_verified, agent_name_set, key_cap_approved), a status, and automatically provides the agent_id once complete, saving the user from copy-paste. It also describes the polling cadence, implying a safe read operation. However, it doesn't mention potential errors or timeouts, which would be useful for a polling tool.

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 three sentences and includes all necessary context: what to poll, how the onboarding flow works, what the response contains, and how often to poll. Each sentence adds value; there's no filler. It's appropriately sized for a tool with a non-trivial workflow.

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 effectively explains the return values and the onboarding process. It covers the flags, status, and agent_id, and ties into the start_onboarding flow. It lacks error handling or timeout expectations, but for a simple polling operation, it is sufficiently complete.

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 describes the single parameter as 'The session_id returned by start_onboarding,' and the tool description reinforces this by referencing the session created by start_onboarding. With 100% schema coverage, the description doesn't need to add much; it adequately aligns the parameter with the sibling tool. No extra parameter details are needed.

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: 'Poll the setup session you started with start_onboarding.' It specifies the resource (setup session), the action (poll), and distinguishes it from siblings like get_agent_status by focusing on the in-progress onboarding steps and returning per-step flags. The inclusion of the specific flags and the agent_id upon completion further clarify the tool's role.

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 explicitly directs when to use the tool: after start_onboarding, and suggests polling 'every few seconds after handing over the deep link.' It provides context about what is completed in chat versus the browser, but stops short of explicitly naming alternatives or when not to use it. This gives clear usage context but not explicit exclusions.

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