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

Annotations already flag destructive=true and idempotent=true, but the description goes further: it clarifies what is NOT affected (AIs are not switched off, nothing is paused, new tasks can start immediately), redirects to where AIs are actually disabled, and explains repeat-call behavior ('asking again stops nothing more'). It even names the return value stopped_tasks, compensating for the missing output schema.

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?

Front-loaded with the imperative scope statement, then constraint, then alternative, then caveats. The sentences are long and the menu-bar aside is slightly digressive, but each clause prevents a plausible misuse rather than restating the name.

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, no-output-schema, destructive bulk action, everything an agent needs is present: exact scope, authorization condition, sibling alternative, side-effect boundaries, and the shape of the return value. Nothing material is left to inference.

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 no parameter meaning to add; the baseline for a parameterless tool is a 4. The description instead spends its detail budget on scope and return value, which is the right allocation.

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?

States a specific verb and full scope: 'Stops every running or queued task of the owner's account, on every computer and in every app, whichever AI started it.' It explicitly contrasts with the sibling 'cancel', so an agent can route between the two without inspecting either 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?

Gives an explicit trigger condition ('only when the owner asks you to stop everything') with example utterances, and names the alternative tool for the narrower case ('to stop one task use cancel'). When-to-use and when-not-to-use are both present.

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