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

Beyond the destructiveHint=true annotation, the description discloses the full blast radius (code, manifest, artifacts, per-viewer state and images, share links, team roles, review history), the external side effect (leaves the app store, URLs stop working at once), the irreversibility ('no undo and no archive'), and the not-found behavior for first-party or non-owned apps. This is materially richer than the annotations.

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 purpose is front-loaded and every clause carries real information (destruction scope, side effects, exclusions, alternative). It is dense and runs long as a single sprawling sentence, which costs a point on structure but not on relevance.

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?

With annotations covering the safety profile and no output schema required, the description supplies everything an agent needs: irreversibility, side effects, ownership/not-found behavior, the confirm gate, and the safer sibling for the publish/unpublish case. Nothing material is left to inference.

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%, so baseline is 3. The description adds an operational precondition for confirm that the schema does not state ('pass confirm: true only after the user said to delete this app by name'), and reinforces the ownership constraint on app_id, though it largely restates the schema's 'not found' wording.

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 ('Delete an app YOU own, for good') and enumerates exactly what the deletion covers. It explicitly contrasts with the sibling unpublish_app and with delete_dataset semantics ('your datasets are NOT touched'), so an agent can distinguish it without opening a schema.

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?

Gives an explicit precondition for use ('pass confirm: true only after the user said to delete this app by name') and names the alternative for the adjacent intent ('to just take it off the store use unpublish_app instead'). When-not-to-use is also covered by the ownership and first-party app exclusions.

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