poll_run_events

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

Annotations declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is well covered. The description adds the notion of 'live' events and 'monotonic cursor' semantics, which hints at streaming/polling behavior. However, it doesn't disclose pagination behavior, whether it returns new events only, or how the after_sequence cursor works in practice — which is the core behavioral trait of a polling endpoint.

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?

One crisply written sentence with zero filler. It's terse to the point of being cryptic, but every word earns its place and there's no wasted content. Front-loads the action ('Read') immediately.

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?

The presence of an output schema helps reduce the completeness burden, and annotations cover safety. But the description misses key operational context: this appears to be a polling/streaming tool (lifecycle events after a cursor), and the description doesn't explain the event lifecycle, how the cursor advances, or whether this returns incremental or cumulative events. Sibling get_run_events likely contrasts in some meaningful way that's undocumented.

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 description coverage is 0%, so the description must compensate by explaining the three parameters. It partially does: 'after a monotonic cursor' gestures toward after_sequence, and the tool name implies polling semantics. However, it doesn't explicitly explain limit, after_sequence's meaning, or run_id's role beyond the obvious schema. The guidance is implied rather than explicit, but the concept is serviceable for a small 3-param tool with clear names.

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 'Read live lifecycle events after a monotonic cursor' identifies the verb (read) and resource (lifecycle events), but it's terse and somewhat jargon-heavy ('monotonic cursor' assumes technical knowledge). It doesn't differentiate from sibling get_run_events, which likely does the same thing with a different mechanism.

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?

No guidance is provided on when to use this tool versus alternatives. The sibling get_run_events exists alongside it, and the description gives no hint about why an agent should choose poll_run_events over get_run_events or when either would be appropriate. The concept of polling with an after_sequence implies a use case, but it's unstated.

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