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

Annotations already declare readOnlyHint: false and destructiveHint: false, so the safety profile is partially covered. The description adds a meaningful behavioral detail: existing waiting runs are preserved, only new starts are blocked. This goes beyond the annotations and clarifies the non-destructive nature, which is valuable for an agent deciding whether to call it.

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 description is two sentences with zero filler. The core action is front-loaded, and the key behavioral distinction is stated immediately. Every sentence carries information that aids tool selection and correct invocation. This is an ideal size for a simple action tool.

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 tool with one required parameter and no output schema, the description covers the main effect but leaves ambiguities: it does not specify what happens to currently executing runs (only 'waiting' ones), whether the stop is reversible, or how to restart. These gaps are minor for a simple stop action but could affect an agent's decision in some scenarios.

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 50% description coverage – workspaceId is explained, but id is not described. The tool description mentions neither parameter, providing no additional meaning for id, which is required. Given the low schema coverage, the description should compensate, but it fails to do so. The agent must infer id semantics from the context alone.

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 and resource: 'Stop an automation.' It clearly indicates the tool halts automation, and the added detail about runs waiting for a button distinguishes it from purely starting or creating automations. It doesn't explicitly name alternative tools, so it loses a point for no sibling differentiation.

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 behavioral note 'Runs already waiting for a button stay waiting but nothing new starts' implies the intended use case (stop new starts while letting pending manual steps continue). However, it does not explicitly state when to use this over alternatives like disable or delete, nor does it mention any prerequisites or exclusions. The guidance 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.