save_waveformSaves a custom timed sequence of suction, vibration, and stop actions, enabling precise playback of device control patterns.
按时间偏移保存自定义动作序列，事件为 [{at:秒, action:suction|vibration|stop_vibration|stop_device, level?:1-100}]。
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| events | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden, yet it says nothing about persistence scope, whether an existing waveform with the same name is overwritten, or whether saving triggers device actions. It only documents the payload shape, leaving the effects of the mutation undisclosed.
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 dense sentence, front-loaded with the action and immediately followed by the payload grammar. Nothing is redundant.
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?
An output schema exists so return values need no explanation, and the events grammar is fully covered. But with zero annotations and an undocumented 'name' parameter, key calling information (naming rules, overwrite semantics, device binding) is missing.
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 events is an untyped array of free-form objects, so the description does real work by fully specifying the event object: 'at' in seconds, the closed set of action values, and 'level' 1-100. The 'name' parameter remains completely unexplained (uniqueness, role), which keeps it from a 5.
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+resource: saving a custom action sequence (waveform) indexed by time offset. The phrase "自定义动作序列" implicitly distinguishes it from the sine/intent waveform creators and from save_recording_as_waveform, though no sibling is named explicitly.
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 on when to use this versus create_sine_waveform, create_intent_waveform, or save_recording_as_waveform, and no preconditions (e.g. does it require a connected device? overwrite an existing name?). The agent must infer usage entirely from the name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.