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

Annotations already mark destructiveHint=true and readOnlyHint=false; the description adds concrete impact—removes microVM, image, route, and data—and the two-phase staging behavior plus authentication need. This goes beyond the annotation flags and gives an agent the true risk profile.

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?

Three tight sentences: what the tool does, why it is dangerous, and exactly how to proceed. Every clause earns its place and the destructive warning is prominently front-loaded.

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?

Despite having no output schema, it states the return (actionId), the required confirmation flow, and the authentication precondition, which is enough for an agent to call this correctly. A minor ambiguity is that 'the summary' is referenced without clarifying its source, so I stop short of the top score.

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 already describes both parameters with 100% coverage: appId is sourced from osirAppList and sessionKey has explicit usage conditions. The description adds no parameter-level syntax or formatting; it remains at the baseline because the schema carries the semantics.

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 ('stage deletion') and precise object (Osir app), and lists the concrete resources removed, making clear it is the app-deletion staging tool and distinguishing it from generic delete tools. The description goes beyond the annotation title by naming the microVM, image, route, and data scope.

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?

Clearly explains the workflow: return an actionId, present the summary to the user, and only invoke executeConfirmedAction with that actionId upon approval. It also notes the authentication requirement; while it doesn't explicitly list when not to use it, the confirmation gate leaves no ambiguity about appropriate use.

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