Recent DualStream events

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

Annotations already mark the tool as read-only, but the description adds substantial behavioral context: buffered events, eviction semantics with truncated flag, server-side receipt timestamps, and the meaning of stream_event entries. This goes well beyond the annotation without contradicting it.

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?

In just three sentences, the description packs the event list, ordering, parameter usage, truncation handling, timestamp origin, and use case distinction. It is front-loaded and every sentence 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?

Despite lacking an output schema, the description explains event types, ordering, truncation semantics, and timestamp provenance, and cross-references get_state_snapshot for resync. It misses explicit response structure but is sufficiently complete for a polling tool.

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 schema already describes both parameters (100% coverage), but the description adds practical usage context, especially for since_seq (polling pattern) and the implication of truncated=true. This enriches the schema's basic definitions.

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 opens with a specific verb ('Poll') and resource ('buffered control events'), enumerates the event types covered, and clarifies ordering ('oldest first'). It also distinguishes itself from wait_for_event by positioning itself for catch-up versus live reaction, fully differentiating from siblings.

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?

Explicit usage guidance is provided: pass since_seq to get only new events, resync via get_state_snapshot when truncated=true, and use wait_for_event for live reaction instead. It also mentions the intended catch-up use case, giving clear when-to-use versus alternatives.

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