watch_log_stop

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, but the description still adds a genuinely useful behavioral fact: collected events persist and remain reachable via watch_log_poll. That tells the agent stopping is lossless, which the annotations do not convey.

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?

Two short sentences, zero filler, with the action stated first and the retention caveat second. Every clause earns its place.

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?

For a zero-parameter control tool with rich annotations, coverage is nearly complete: what it does, that data persists, and where to get it. Only the not-running/no-op edge case is left to the idempotentHint annotation rather than stated outright.

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 tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a no-param tool is 4.

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?

"Stop the background log watcher" is a specific verb+resource, and the second sentence names the sibling (watch_log_poll) that receives the retained output, which cleanly separates this from watch_log_start. An agent can identify the operation without opening the schema.

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 usage context is implied (stop the active watcher) and the description routes to watch_log_poll for retrieval, but it never states when stopping is appropriate or whether it is safe to call with no watcher running. No explicit when-not or prerequisites are given.

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