wait_for_2fa

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

With no annotations, the description carries the full behavioral burden, and it delivers: backoff algorithm details ('exponential backoff (2s initial, 1.5x, 30s max) with jitter'), terminal states, the 'pending' status on timeout, an ACCESS prerequisite (PROOF_API_KEY, server restart), and a negative behavioral note (start_login does not open it). This is comprehensive behavioral disclosure far beyond what any annotation would have provided.

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 long but every sentence earns its place, covering purpose, backoff, workflow, terminal-state handling, challenge presentation, and access. It is clearly organized into labeled sections ('Agent usage:', 'ACCESS:') and front-loaded with the core purpose and backoff policy in the first sentence. The density is justified by the actionable operational detail.

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?

Despite lacking an output schema, the description covers all return semantics via terminal states ('verified', 'expired') and the schema covers the 'pending' timeout case. The agent knows the prerequisites, the call sequence, how to render the challenge, and what to do on each outcome. For a two-parameter polling tool, nothing an agent needs to call it correctly 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 coverage is 100% and both parameters are already well-documented in the schema, including the timeout_seconds default, max, and timeout edge-case behavior. The description reinforces that session_id comes from start_2fa's return, matching the schema's '2FA session ID from start_2fa.' It adds workflow context but no new semantic information beyond the schema, so the baseline of 3 is appropriate.

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 opening sentence, 'Poll a 2FA session until the user completes the challenge,' uses a specific verb (poll) and resource (2FA session) with a clear goal. It differentiates from siblings like get_2fa_status (a one-shot status check) and verify_2fa (a submission action), and explicitly declares what it is not: 'start_login does NOT open this tool.'

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 gives an explicit workflow: 'Call this after start_2fa with the returned session_id.' It specifies what to do on each terminal state ('verified' → proceed with the protected operation, 'expired' → offer to restart with start_2fa) and how to present the challenge (render_auth_link for deep_link, show sms_message for sms). It even names the alternative that does NOT open this tool, leaving no ambiguity about sequencing.

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