device_recent_events

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is known. The description adds valuable behavioral context beyond the annotations by specifying that this is a one-shot read of a bounded in-memory buffer ('still holds', 'typically the last 10'), which helps the agent predict behavior and result size.

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 a single, front-loaded sentence with no filler. Every phrase contributes meaning: operation type, resource scope, bounded depth, and the optional events/frames distinction.

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 the tool's simplicity, the presence of an output schema, and read-only annotations, the description covers the essential invocation context. Minor gaps remain about how to request frames vs events explicitly and what happens when no events are available, but the schema enum and output schema cover much of the remaining burden.

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 help interpret parameters. It does indirectly: 'events (or frames)' maps to the kind enum, and 'for a device' maps to dev_eui. However, it never names the parameters explicitly or explains dev_eui format/requirements, relying on the schema's required field and enum.

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 clearly states the action ('one-shot look') and resource ('last few events or frames ChirpStack still holds for a device'), including the expected depth ('typically the last 10'). It does not explicitly name sibling tools, but 'one-shot' and 'still holds' help differentiate it from live/waiting or broader metrics 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?

The description implies use for a quick snapshot of a device's most recent buffered data, and 'typically the last 10' suggests limited depth. However, it gives no explicit when-to-use or when-not-to-use guidance, nor does it name alternatives such as wait_for_event or device_metrics.

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