send_notification

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does well by detailing the automatic format adaptation across multiple channels (e.g., '飞书：Markdown 卡片消息', '钉钉：Markdown（自动降级标题为 ###）'), which is crucial behavioral context. However, it doesn't mention potential rate limits, authentication requirements, or error handling for failed sends, leaving some gaps for a tool with no annotation coverage.

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 efficiently structured: it starts with the core purpose, immediately details format adaptation across channels (critical context), provides a usage tip with alternative tool reference, then clearly documents parameters and returns with examples. Every sentence adds value, and the information is front-loaded with the most important behavioral details first.

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 complexity (multi-channel sending with format adaptation), no annotations, 0% schema coverage, but with an output schema (Returns JSON格式的发送结果), the description is remarkably complete. It covers purpose, behavioral traits (format adaptation), parameter semantics, usage guidance with alternatives, and examples. The output schema handles return values, so the description appropriately focuses on input and behavior.

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?

With 0% schema description coverage (schema provides no descriptions for parameters), the description fully compensates by explaining all three parameters: 'message: markdown 格式的消息内容（必需）' clarifies format and requirement; 'title: 消息标题，默认 "TrendRadar 通知"' specifies default value; 'channels: 指定发送的渠道列表...' lists all possible values and behavior when unspecified. This adds significant meaning beyond the bare schema.

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 specific action ('向已配置的通知渠道发送消息' - send messages to configured notification channels) and resource (notification channels). It distinguishes itself from sibling tools like get_notification_channels (which retrieves channels) and get_channel_format_guide (which provides formatting guidance) by focusing on the sending operation.

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 provides explicit guidance on when to use this tool versus alternatives: it mentions '发送前可调用 get_channel_format_guide 获取目标渠道的详细格式化策略' (before sending, you can call get_channel_format_guide to get detailed formatting strategies for target channels), clearly indicating an alternative tool for pre-send formatting checks. It also specifies that channels can be specified or left to default to all configured channels.

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