get_device_events

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is fully covered. The description adds two pieces of real context — events are persistent (retained, so historical fetches are valid) and idempotent-by-cursor polling — but says nothing about retention window, ordering, or volume of events returned.

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?

A single compact sentence that front-loads what is read and then gives the operational instruction. No filler, nothing to cut.

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 output schema exists, so return-value explanation is not needed, and the cursor mechanic is covered. Still, an agent cannot tell from the description how far back events persist, whether they arrive in ascending order, or what limit does — gaps that matter 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?

Schema description coverage is 0%, so the description must carry the parameter burden. It explains after_id well (cursor to the last seen event id), but 'limit' is never mentioned and its default of 100 and bounds are undocumented in both places.

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?

States a specific verb and resource — reading persistent connect/disconnect events — which is clearly distinct from every sibling (no other event-stream tool exists; start/stop_device_monitor are about monitoring, not reading history). It does not explicitly name how it relates to the monitor tools, but the resource itself disambiguates.

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?

'Pass the last event id to fetch new events' implies the polling/cursor usage pattern, which is genuinely useful guidance. However, it gives no when-to-use vs. when-not, and does not say whether this should be used instead of or alongside start_device_monitor for live event capture.

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