ddb_poll_rolls

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

With no annotations provided, the description carries the full behavioral burden and meets it well. It says the tool 'drains' rolls, implying it consumes the buffer (a state-changing behavior), and warns 'never re-roll' to prevent incorrect use of the returned dice values. It also specifies the return structure (seq, summary, raw message), giving the agent a clear expectation of the output without an output schema.

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 compact—two sentences—with no filler. The core purpose is front-loaded, followed by the return format, then a usage guidance sentence that also carries the vital 'never re-roll' warning. Every sentence earns its place, and the structure is easy to parse.

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 tool with one parameter, no output schema, and straightforward behavior, the description is fully complete. It covers the purpose, the return structure, the parameter semantics, and the critical behavioral constraint (never re-roll). There is no missing information an agent would need to call this tool correctly.

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 provides a thorough description of `after` (return rolls with seq > after, use the previous cursor, default 0) with 100% coverage. The description adds a small but useful nuance by clarifying that omitting `after` returns everything buffered, which reinforces the default behavior. This goes slightly beyond the schema without being redundant, so it merits a 4.

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 ('drain') and resource ('dice rolls the pump has captured'), and clarifies the scope ('since a cursor'). It also states what the tool returns, making the purpose unambiguous. It clearly differentiates from sibling tools like start/stop_ddb_roll_pump and ddb_roll_pump_status, which manage or report pump state rather than drain rolls.

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 gives explicit instructions on how to use the tool: pass the previous response's cursor as `after`, start with 0 (or omit) for everything buffered. It also provides a critical usage directive for the bridging scenario: 'mirror its actual dice values when bridging — never re-roll.' This directly tells the agent when and how to use it, leaving no ambiguity about the polling workflow.

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