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

Annotations already mark the tool as destructive (destructiveHint: true). The description adds context by stating it mutates infrastructure, specifying the return code '202 Accepted', and advising to track via get_operation. This provides useful behavioral context beyond the annotation.

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 concise with three sentences, each serving a distinct purpose: declaring the mutation, explaining the scope parameter, and noting the API endpoint and tracking method. No superfluous information.

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 two parameters, one required, no output schema, and existing annotations, the description adequately covers the action, parameter behavior, return status, and tracking. It could mention potential side effects beyond the destructive hint, but overall is complete.

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?

Schema coverage is 100% with both parameters having descriptions. The description adds value by explaining the effect of omitting scope (restart all) versus providing specific process types, which enhances understanding beyond schema definitions.

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 clearly states the tool restarts an app's containers, specifies the action 'restarts', and identifies the resource as 'an app's containers'. It distinguishes from sibling tools by explicitly declaring it mutates infrastructure, which sets it apart from read-only or other mutation tools.

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 description explains the optional scope parameter and its effect, providing implicit guidance on when to include it. However, it does not explicitly address when to use this tool versus alternatives like scale_app or trigger_deployment, which are present in sibling tools.

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