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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The description still adds real value beyond them: cascade side effects (credentials revoked, report access removed) and the preview-vs-commit gating rule. It stops short of stating irreversibility or whether the preview result differs in shape.

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?

Two sentences, zero filler, and the destructive consequence is front-loaded ahead of the gating instruction. Every clause carries actionable 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?

With an output schema present, return values need not be described, and annotations cover the safety hints. The description supplies the remaining agent-critical knowledge: what gets destroyed and the preview/commit workflow. Nothing needed to invoke this correctly is missing.

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 0% with a nested confirmation object, so the description must carry the meaning — and it does: it explains that confirmation must be omitted for preview and must match operation/appId for the real delete, which is the non-obvious semantic. appId itself is left to the schema's pattern/length constraints, which is acceptable.

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?

Specific verb + resource ("Delete an app") plus the full blast radius ("revoke credentials and remove report access"), which tells the agent exactly what collateral state is destroyed. This clearly separates it from the non-destructive siblings (rename_app, update_reporter_settings, regenerate_sdk_key) without needing to open any 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?

It gives an explicit two-phase protocol: omit confirmation to get a preview, and only supply a matching operation/appId after explicit user intent. That is a concrete when-to-call-this-way rule rather than an implied one, and it is the single most important decision an agent faces with a destructive tool.

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