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

With no annotations, the description carries full behavioral disclosure burden and meets it well. It discloses read-only safety, cursor semantics, the empty-initial-result behavior, ordering, inclusion of reversals, and the need to poll repeatedly. This is substantive behavioral context well beyond the title.

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 concise sentences pack in action, cursor workflow, edge-case behavior, and safety guidance with no filler. The essential 'drain since cursor' semantics are front-loaded, and every clause 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?

For a two-parameter tool with no output schema and no annotations, the description explains the calling pattern and return behavior sufficiently. It could be slightly more explicit about how a caller knows the drain is complete beyond 'call repeatedly,' but it is otherwise complete for an agent to invoke and iterate 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?

Schema coverage is 100%, so baseline is 3, but the description adds useful cross-call semantics for `since`: it explains it starts from now when omitted and that the returned cursor should be reused. This goes slightly beyond the schema's 'Opaque cursor from a previous call' phrasing.

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 states a specific action ('Drain decisions whose state changed') and a specific resource, clearly distinguishing it from siblings like query_decision and whoami. The phrase 'Read-only; poll this on a schedule' further reinforces that this is a streaming/change-feed tool, not a query tool.

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 clear, actionable usage context: call with no `since` for an initial empty set and cursor, then repeat with the returned cursor to get ordered changes. It does not explicitly name query_decision as the alternative for point-in-time reads, so it misses the 'when-not-to-use' exclusion, but the polling context is otherwise clear.

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