message.watch

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

With no annotations, the description carries the behavioral burden and does disclose the key live-stream traits: it is persistent, outputs JSONL to stdout, and terminates via Ctrl-C. However, it does not mention authentication requirements, reconnection/error behavior, or the lifecycle/side effects of starting a long-lived connection.

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 entire description is a single compact sentence that front-loads the core behavior (persistent IM long connection) before giving output format and exit method. Every phrase earns its place and no filler is present.

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?

The description is adequate for invoking a parameterless streaming tool: it explains output format and how to stop it, and an output schema exists. It is less complete for tool selection because it never clarifies which events are included or how this relates to the extensive watch.* and message.* sibling set.

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 and 100% schema description coverage, so there are no parameter semantics for the description to clarify. The tool is essentially parameterless, and the description adds no unnecessary parameter detail.

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?

Description identifies a specific action: maintain a persistent IM long connection and stream downstream events as JSONL to stdout. It is mostly clear, but it does not explicitly differentiate message.watch from the many watch.* sibling tools (e.g. watch.start, watch.run), so there is some selection ambiguity.

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 is given about when to use this tool versus alternatives such as message.history or watch.start. The only implied signal is that it is a live, long-running stream, but the description does not state exclusions, prerequisites, or when another tool would be preferable.

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