wait_for_event

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

With no annotations, the description carries the full burden and does disclose the important traits: a bounded blocking wait (timeout), an empty-list return rather than an error on no activity, and the loop-termination condition. It omits auth requirements, whether the wait is a true long-poll versus sleep, and concurrency caveats, so it is good but not exhaustive.

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 tight sentences, front-loaded with what is being waited on, then the parameter contract, then the return/loop semantics. No filler.

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?

For a 3-parameter polling tool with an output schema, the description covers the essential loop contract and return-on-empty behavior; because an output schema exists it need not detail the event payload shape. Only the call_id semantics and any failure behavior are unaddressed.

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 0%, so the description must compensate, and it does for two of three parameters: timeout is in seconds and after is the highest seq already seen (with a default implied by the polling loop). call_id is never explained, though its meaning is inferable from the resource context.

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?

Specific verb (wait) plus resource (new events on a call) and an enumeration of the event kinds that can arrive (questions, progress reports with stage/note, call ended). It is unmistakably a long-poll primitive rather than a state read, though it never names a sibling (e.g. get_call) to sharpen the boundary.

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?

Gives concrete operating instructions: pass the highest seq seen so far as after, expect an empty list when nothing happened, and re-call until status is 'done' or 'failed'. That is clear when-to-use guidance for the polling loop, but no alternative tool or condition for preferring get_call over waiting is mentioned.

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