Await case activity

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

Beyond the readOnlyHint annotation, the description discloses blocking semantics, timeout behavior, the return shape ({events, latestCursor, timedOut, waitedS, ...}), and a clear re-arm protocol. It also warns against infinite loops and instructs the agent to tell a human instead, which is exactly the kind of behavioral context annotations cannot convey.

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-load the core action and then provide the critical protocol. Every sentence earns its place: what it does, how to resume, and how to avoid infinite polling. There is no filler or repetition of schema basics.

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 long-polling tool with no output schema, the description explains the return fields, the timeout edge case, the continuation cursor, and the stopping condition. It covers everything an agent needs to invoke and re-invoke the tool correctly, including a human-escalation path for stale cases.

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%, so the baseline is already strong. The description adds genuine semantic value by explaining how `after` relates to `latestCursor`, why `timeoutS` matters for re-arming, and what 'timedOut' means in practice. It does not elaborate on `types` or `caseId`, but the schema already documents those adequately.

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 uses a specific verb ('Block until'), names the exact resource ('a case'), and clarifies the behavior is a long-poll for NEW events. This clearly differentiates it from sibling tools like get_case_activity and await_verdict without needing to open their schemas.

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 provides explicit operational guidance: omit `after` to watch from now, re-arm with the returned `latestCursor`, and stop re-arming once `caseEndsAt` is well past. It does not explicitly name alternative sibling tools for the 'when not to use' case, but the re-arm and stop-looping protocol is strong and contextually complete.

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