poll_task_events

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

Description clearly labels as WRITE/LOCAL, describes side effects (durably stages, advances checkpoint), and declares observation-only nature. With no annotations, this adequately covers behavioral traits.

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 sentences, front-loaded with operation type, no wasted words. Each sentence adds distinct value.

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 simplicity (1 non-required param, no output schema), description covers purpose, behavior, and usage. Could briefly explain what 'deterministic event envelopes' are, but overall adequate.

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?

Single parameter has schema description (coverage 100%), so baseline is 3. Tool description does not add any further meaning beyond the schema.

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?

Description uses specific verbs (diffs, stages, advances) and mentions return type. It hints at distinction from siblings (e.g., unacknowledged pending spool) but could explicitly differentiate from acknowledge/list/snapshot tools.

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?

States events are observation-only and must be acted on separately, implying usage pattern. But does not explicitly state when to use this tool vs siblings like acknowledge_task_events or list_pending_task_events.

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