message_watch

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

With no annotations provided, the description shoulders the transparency burden. It discloses key behavioral traits: the long-lived nature ('常驻'), output format (JSONL to stdout), and termination method (Ctrl-C). This goes beyond a bare restatement of the name, though it omits potential details like reconnection behavior or error handling, which are less critical for a simple watch tool.

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 sentence that is front-loaded with the key concept ('常驻 IM 长连接'), followed by output specifics and exit instruction. Every word contributes meaning without redundancy or fluff.

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 has zero parameters and an output schema exists, the description adequately covers the tool's purpose, mode of operation, and termination. It tells the agent what to expect (JSONL stream) and how to stop it, making it sufficient for safe invocation. No additional context is necessary.

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?

The input schema has zero parameters, so the baseline is 4. No parameter documentation is needed, and the description focuses on the tool's behavior, which is appropriate for a parameterless tool.

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 identifies the tool as a persistent IM long connection that outputs downstream events as JSONL to stdout, and mentions exit via Ctrl-C. This distinguishes it from siblings like message_history (past messages) and message_send (sending), establishing a specific watch/stream scope.

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 usage for live event monitoring ('常驻' meaning resident/continuous) and provides exit instructions, but it does not explicitly state when to prefer this over alternatives like message_history for historical data. No exclusions or alternative tool names are given, leaving usage guidance implicit rather than explicit.

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