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 genuinely non-obvious detail: 2fa_code values are single-read and wiped after 10 minutes. It is silent, however, on whether polling has side effects for other request types and on rate limits, so the disclosure is strong but not complete.

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?

Two tight sentences with no filler; the state enumeration and the exceptional 2fa_code caveat are both front-loaded and each earns its place.

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?

No output schema exists, so the description must frame the response, and it does so only for the 2fa_code case; it never says what a poll returns for other statuses or how often to poll. Adequate for a simple poll endpoint, but an agent must still guess at cadence and payload shape.

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 single request_id parameter has 0% schema description coverage and the description never mentions it, so it adds no semantic detail about the ID's origin or format (presumably returned by request_human). For a trivial one-string-param tool this is a minor gap, but the description does not compensate for the coverage hole.

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 ('Poll') and resource ('a request'), then enumerates the terminal and intermediate states (pending, done, approved, denied, code_ready, expired, cancelled), which makes the tool's role legible at a glance. It doesn't explicitly contrast itself with siblings like cancel_request or request_human, but 'poll' vs 'cancel'/'request' is unambiguous in practice.

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?

Usage is only implied: the status list tells the agent to keep polling until a terminal state, but there is no guidance on polling cadence, whether repeated polls are cheap, or which alternative to use when the caller actually wants to cancel or create a request. No explicit when-not conditions are given.

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