Delete app

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

The description adds substantial behavioral context beyond the annotations: tombstone semantics (data/files/history kept), cascade's two-step confirmation with disposition plan, and the permanent, non-undoable nature of cascade. It also clarifies that shared or unprovable collections are always kept, which is critical for understanding the tool's impact. No contradiction with annotations; destructiveHint and idempotentHint are consistent.

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 dense but efficient; every sentence adds critical information about behavior or usage. It is front-loaded with the primary action and then elaborates on modes and confirmation. Slightly lengthy due to the complexity of the cascade flow, but still concise given the tool's nuance.

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 tool with no output schema, the description is remarkably complete. It covers the two deletion modes, the irreversible-cascade chain, the disposition plan requirement, and the preservation rules for shared/unprovable collections. This provides enough context for an agent to execute correctly and explain the outcome to a user.

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 description significantly enhances understanding of the 'data' parameter by explaining tombstone vs cascade and the request_state flow. However, it does not cover the semantics of 'name', 'actor', or 'command_id' beyond the schema (which itself omits descriptions for name and actor). With schema coverage at 60%, the description partially compensates but leaves some param meanings implicit.

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 'Delete an app from the registry' — a specific verb and resource. It further distinguishes two deletion modes ('keep' tombstone vs 'cascade' permanent) and explicitly references restore_app as the undo path, setting it apart from sibling tools like restore_app and file_delete.

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?

Provides explicit guidance on when to use each mode: use 'keep' for a reversible tombstone and 'cascade' for permanent deletion. It instructs the agent to read the disposition plan to the user and re-send with request_state, effectively outlining the confirmation workflow. Also warns that cascade is not undoable and that shared/unprovable collections are always kept, helping the agent decide appropriately.

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