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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description adds real behavioral context on top: the two-minute wait cap, that the wait terminates with the call, that answers received during reconnects are still included, and that in-progress forms still return. Return format detail is limited but the useful traits are disclosed.

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?

Three dense sentences, front-loaded with the core behavior (wait, return on answer) before the continuation protocol and the SSE aside. Little waste, though the SSE mention is tangential to invoking this tool.

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 does the heavy lifting on returns by naming nextSince and the answer-arrival trigger. The polling loop, timeout ceiling and reconnection behavior are all covered. The precise return shape is implied rather than spelled out, which is the only gap.

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 40%: since and timeoutMs are documented in the schema, and the description reinforces both (nextSince as the cursor, 'up to two minutes'). url, askId and agentToken get no semantic explanation anywhere. The description partially compensates but leaves the majority of parameters unexplained.

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 gives a specific verb and resource: wait (poll) and return once an individual answer is saved, with a two-minute ceiling. An agent can tell this is a blocking single-answer watcher rather than a form-level fetch. It does not explicitly name the sibling it differs from (e.g. watch_my_form_responses), so it stops short of full differentiation.

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 states the polling contract clearly: call returns when an answer arrives, the wait ends there, nothing keeps watching, and nextSince should be fed back as since to continue. It also points to the SSE stream endpoint as an alternative mechanism. It does not state when to prefer this over watching whole-form responses.

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