unwatch

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

With no annotations provided, the description carries the behavioral burden. It honestly discloses that the tool mutates state by stopping the polling loop. It does not mention idempotency or error behavior when no loop is running, but the core side effect is clearly named.

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, front-loaded with the primary action, and zero filler. Every word contributes to understanding what the tool does and how it relates to 'watch'.

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 no-argument control command with no output schema, the description is complete. It explains the action, the target resource, and the relationship to the starting command. Nothing essential is missing for an agent to invoke it correctly.

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 has zero parameters, so there is no parameter semantic burden on the description. The schema already fully covers the empty parameter set, and the description adds no unnecessary parameter detail. Baseline 4 is appropriate.

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 states a specific verb ('Stop'), the resource ('auto-watching the Notion Watchlist'), and the mechanism ('Stops the polling loop started by watch'). It clearly distinguishes itself from its sibling tools, especially the paired 'watch' tool.

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?

It explicitly ties usage to stopping the loop started by 'watch', making the intended call context clear. It does not enumerate alternatives or edge cases like calling when no watch is active, but for a simple stop command this is sufficient guidance.

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