DESTRUCTIVE: Permanently delete an app, its Docker service, volume, and all data including version history. This cannot be undone. You MUST confirm with the user before calling this tool.
| Name | Required | Description | Default |
|---|---|---|---|
| app | Yes | App ID (UUID) or subdomain |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully discloses the destructiveness: it permanently deletes the app, Docker service, volume, and all data including version history, and states 'This cannot be undone.' This goes well beyond structured data and alerts the agent to irreversible side effects, which is exactly what an agent needs for safe invocation.
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 compact and front-loaded with the DESTRUCTIVE warning, followed by a precise list of what gets deleted and the irreversibility, then the mandatory confirmation instruction. Each sentence carries critical information with no wasted words.
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?
Given the tool's irreversible destructive nature, no annotations, and no output schema, the description provides all essential context: what is affected, that it can't be undone, and that user confirmation is required. Sibling tools do not need explicit comparison because the deletion scope is unambiguous.
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 input schema fully documents the single parameter 'app' as 'App ID (UUID) or subdomain' (100% schema coverage). The description adds no additional parameter-level detail, so it meets the baseline of 3 but does not exceed it.
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 uses the specific verb 'Permanently delete' with a clear resource ('an app') and enumerates the exact scope ('its Docker service, volume, and all data including version history'). This distinguishes delete_app from sibling tools like delete_file and stop_app, making the tool's purpose unmistakable.
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 clearly implies when to use this tool: when the user wants permanent, irreversible deletion of an app. The explicit 'You MUST confirm with the user before calling this tool' provides a critical usage prerequisite. However, it does not explicitly contrast with alternatives like stop_app or restart_app, so it stops short of full when-not guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have clearly distinct purposes, but a few pairs could be confused: get_app vs. get_app_status both report on app state, and update_app vs. set_node_version both modify runtime configuration. Descriptions are detailed enough to mitigate most ambiguity, but the overlap is notable.
Tool names largely follow a consistent verb_noun snake_case pattern (e.g., list_apps, create_app, delete_file). Minor deviations include the bare verb 'login' and the noun-first 'git_info', which break the pattern slightly but are still understandable.
At 37 tools, the set is on the heavy side, well above the typical 3-15 range. However, the server covers a broad PaaS domain (auth, app lifecycle, file management, packages, versions, git, metrics), and each tool addresses a distinct operation. It feels over-engineered in places but not gratuitously so.
The tool surface is impressively complete for a deployment platform: authentication, app CRUD, start/stop/restart, file operations (read/write/delete/rename/search/upload), package management, version snapshots and restore, git remote and push/pull, logs, metrics, and configuration. No critical dead-ends are apparent.
