Read buffered device events, such as button presses, in order. Start with a null cursor, continue with next_cursor, and reset to null after history_lost or cursor_reset.
Read buffered device events (for example button presses) in order. Start with a null cursor, then pass next_cursor. On history_lost or cursor_reset, read again with a null cursor.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| cursor | No | ||
| device_id | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, non-destructive, closed-world), and the description adds real behavioral detail beyond them: pagination via cursor, in-order delivery, and the recovery protocol for history_lost/cursor_reset error states. Only the shape of returned events and the meaning of an exhausted stream remain unstated.
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 tight sentences, front-loaded with the core action, then the pagination contract, then the error-recovery rule. Every sentence carries instruction the agent needs and none is padding.
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?
No output schema exists, so the description should ideally say what an event looks like or that the response carries next_cursor and the empty/end-of-stream signal. It covers the read loop but leaves result shape, limit semantics, and device filtering unspecified, so it is only adequately complete for a 3-parameter paginated reader.
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 0% and none of the three parameters carry descriptions, so the description must compensate. It explains the cursor lifecycle well (null to start, next_cursor thereafter) but leaves 'limit' (default 32) and especially 'device_id' filtering completely unexplained; it also names the value 'next_cursor' where the schema names it 'cursor'.
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?
Specific verb+resource ('Read buffered device events') with a concrete example (button presses) and an ordering guarantee ('in order'). It reads distinctly from siblings like gadgets_get_state or gadgets_list_devices, though it never explicitly contrasts itself with them.
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?
Gives procedural invocation guidance (start with null cursor, then pass next_cursor, re-read with null cursor on history_lost/cursor_reset), which is genuinely useful. It does not, however, say when to prefer this over gadgets_get_state or the other siblings, so usage selection is left implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.