wait_for_2fa

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

Annotations only declare readOnlyHint=true; the description goes far beyond by disclosing the backoff schedule (2s initial, 1.5x, 30s max, jitter), timeout behavior (returns 'pending' and must be re-called with the same identifier), terminal states, and an auth prerequisite (Proof account, PROOF_API_KEY, restart required). No contradiction with readOnlyHint — polling is a read.

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?

Well front-loaded and sectioned (purpose, agent usage, rendering caveat, access), and every section carries information. It loses a point for the third paragraph, which restates the 'user does not see tool results' rendering point already covered in the usage paragraph.

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 takes on the return-value burden and delivers: the two terminal states, the 'pending' timeout state, and the required follow-up call. Combined with the rendering and auth notes, nothing an agent needs to call this 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 description coverage is 100%, so the schema already documents both session_id and timeout_seconds (including defaults, max, and the client-timeout caveat). The description only adds marginal reinforcement ('with the returned session_id', 'call it again with the same identifier'). Baseline 3 is appropriate when the schema carries the weight.

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 states a specific verb and resource ('Poll a 2FA session until the user completes the challenge') and immediately distinguishes itself from sibling pollers like get_2fa_status by its blocking/polling nature. An agent can tell it apart from wait_for_login, wait_for_session, and verify_2fa 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?

Explicitly prescribes sequencing ('Call this after start_2fa with the returned session_id'), names the terminal states and what to do in each ('expired' → restart with start_2fa), and routes to render_auth_link on telegram/whatsapp vs sms_message on sms. This is when/when-not plus alternatives, fully spelled out.

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