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

Annotations already declare destructiveHint=false and readOnlyHint=false, so the safety profile is covered. The description adds genuinely non-obvious behavior: only new event-triggered runs are blocked, while in-flight runs continue — exactly the fact an agent needs before mutating state. It stops short of saying how to resume or what happens when pausing an already-paused automation.

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, the primary effect is front-loaded, and the qualifier about existing runs follows immediately. No filler.

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 one-parameter mutation with full annotation coverage and no output schema, the description covers the essential semantic question (what does pausing actually stop). Minor gaps remain around resume path and behavior on an already-paused automation, but nothing blocks correct invocation.

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?

There is a single parameter with 100% schema coverage and the schema already documents the aut_xxx ID format. The description adds no extra meaning about the identifier, so the baseline 3 applies.

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 gives a specific verb (Pause) and resource (an automation) plus the concrete effect on the resource. It implicitly separates itself from stop-automation by describing what continues running, but it never names that sibling, so differentiation requires inference.

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 statement that in-progress runs keep going strongly implies when to prefer pause over a hard stop, but no alternative tool (stop-automation, cancel-automation-run, delete-automation) is named and no explicit when-not condition is given. Usage is implied rather than stated.

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