watch_events

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does add some behavior: it is a long-poll (efficient, not busy waiting) and supports reconnection using the last event ID (stateful). However, it does not disclose error handling, rate limits, or what happens on timeout. Given the lack of annotations, it is somewhat useful but still incomplete.

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?

The description is a single sentence that packs two key pieces of information: long-polling without busy waiting, and reconnection using the last event ID. It is concise and front-loads the core purpose. However, it could be slightly more structured to elaborate on parameters while maintaining brevity.

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?

Given the presence of three parameters with no descriptions, an output schema that is not described, and only a brief mention of reconnection, the description is insufficient for an agent to call the tool correctly. The agent knows it is a long-poll but lacks details on parameter usage, response format, or how to obtain the 'last event ID' from the output. These gaps make it incomplete.

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 description does not explicitly explain any parameters. It implicitly refers to 'last event ID' which maps to after_event_id, but it does not clarify the meaning of limit or timeout_seconds. Since schema description coverage is 0%, the description needs to compensate but only does so for one parameter indirectly. The parameter semantics are largely 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 clearly states the tool watches events via long-polling, which is a specific verb+resource. It mentions 'durable events' and 'reconnect' which gives a sense of its function. However, it does not explicitly differentiate itself from the sibling tool 'get_events', which likely provides a comparable event-fetching capability.

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 phrase 'without busy waiting' implies it is for continuous streaming compared to polling, but there is no explicit guidance on when to use this tool versus alternatives like get_events. The description does not mention when it is appropriate to call this tool over others, nor does it state any prerequisites or exclusions.

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