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

Annotations already disclose destructiveHint=true, readOnlyHint=false, and openWorldHint=true, so the safety profile is covered. The description adds little beyond that: it does not explain whether the deployment is removed, whether the live URL stops working, whether data is preserved, or what permissions are required.

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?

A single four-word sentence with no filler, and the key action is front-loaded. Nothing in it is redundant.

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 destructive operation, annotations cover the risk category and the schema covers the sole parameter. However, the description does not describe the concrete effect of unpublishing, which is important context an agent may need before invoking a destructive tool.

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 description coverage is 100%, and the schema itself documents project_id as optional with the session fallback to use_project. The description adds no further parameter meaning, so the baseline of 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?

States a specific verb and resource: "Unpublish the live app." It is clear what the tool does and reads as the inverse of the sibling publish_app, though it does not explicitly name or contrast with that sibling.

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 phrase "live app" weakly implies this applies only to a currently published app, but there is no explicit when-to-use guidance, no prerequisites, and no mention of publish_app as the alternative for the opposite operation.

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