sync_application_with_prune

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

The description explicitly warns that resources present in the cluster but absent from Git state will be DELETED on a live run, and that prune=true is always passed regardless of dry_run setting. Since no annotations are provided, the description carries the full burden and does so well — explaining the always-prune behavior and confirmation requirements. It could mention what the response looks like or how to revert a prune, but the core destructive behavior is thoroughly disclosed.

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 well-organized with a clear lead sentence, the core destructive behavior stated upfront, and bullet points for dry_run modalities and prerequisites. It's efficient and front-loaded with the critical warning. The only minor inefficiency is some redundancy between the lead sentence and the always-prune explanation.

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 Tier-3 tool with no annotations and 0% schema coverage, the description covers the most critical aspects: the always-prune behavior, confirmation flow, and required environment flags. With an output schema present, return-value documentation isn't strictly needed. It could add what happens on preview output or reversal options, but the essential safety-critical context is present.

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%, meaning the description must compensate for all parameter documentation. The description adds meaning for dry_run, confirm, and confirm_name by explaining their interplay (dry_run=false requires both confirm=true and confirm_name match). However, parameters like force, revision, and instance get no additional semantic context beyond the schema's minimal field descriptions, leaving gaps.

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 it synchronizes application and PRUNE cluster resources missing from Git, explicitly labeling it DESTRUCTIVE. It distinctly differentiates from sibling sync_application by highlighting that prune=true is always passed, making the destructive capability unambiguous and distinguishing its purpose.

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 description explicitly explains the dry_run=true default (preview, no confirmation needed) versus dry_run=false (requires confirm=true AND confirm_name matching). It clearly states prerequisites (MCP_READ_ONLY=false and MCP_DISABLE_DESTRUCTIVE=false). This gives explicit when-to-use guidance including confirmation steps and environment requirements.

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