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 thoroughly details the automatic formatting adaptations for each channel (e.g., DingTalk strips <font>, Telegram converts markdown to HTML), revealing internal behavior beyond a simple send. It also notes that results are returned per channel. It does not mention rate limits or auth requirements, but given the context, the formatting adaptations are the most critical behavior and are well covered. A 4 is appropriate.

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 long but well-structured: an intro, channel-specific formatting list, a helpful hint, then Args, Returns, and Examples. Each section serves a purpose, and the channel list is necessary for clarity. It could be slightly condensed (e.g., grouping similar channels), but the organization is logical and front-loads the core purpose. A 4 is fair.

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?

Even though an output schema exists (so return value details are not required), the description covers key usage aspects: parameter semantics, channel adaptations, and a pointer to the format guide. It does not mention error handling or prerequisites like authentication, but these may be covered by output schema or system context. For a sending tool with zero schema coverage, it is quite complete, though a brief note on partial failures could fill a small gap. Score 4.

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 compensate fully. The 'Args' section explains each parameter: message is required, title has a default value, and channels has a clear list of allowed values. It even provides examples showing usage. This adds substantial meaning beyond the bare schema and effectively documents the parameters.

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 tool sends messages to configured notification channels ('向已配置的通知渠道发送消息'). It lists the specific channel types and distinguishes itself from siblings like get_channel_format_guide (which retrieves format strategies) and get_notification_channels (which lists channels). The purpose is unambiguous and well-scoped.

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 get_channel_format_guide before sending to optimize formatting, which helps route the agent to the right sibling. It also clarifies that channels parameter is optional and defaults to all configured channels. However, it does not explicitly state when NOT to use this tool or mention alternative sending-related tools (e.g., get_notification_channels for listing channels), so it falls short of a perfect 5.

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