reinstall_server

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

Although annotations already declare destructiveHint=true, the description adds substantial behavioral context beyond that: 'все данные на дисках будут удалены' specifies exactly what gets destroyed, it names the required environment variable guard, and it discloses the operation is asynchronous with status via check_task. This is precisely the kind of safety and execution-context detail the annotation alone does not provide.

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 — three clauses covering purpose, destructive warning, and execution requirements, with the most critical safety information front-loaded. The cryptic 'eq/order_instance' reference consumes space without adding agent-actionable meaning, but overall the text is efficient.

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, asynchronous mutation with 10 parameters and no output schema, the description covers the essential operational context: data destruction scope, required flags, hostname verification, and how to track completion. The main gap is not naming the sibling alternative (create_reinstall_task) explicitly, leaving the when-vs-alternative decision to the agent.

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 80%, so the input schema already documents the parameters well, including the confirm requirement and the special os_id=0 + own_os=1 meaning. The description adds no additional parameter meaning that the schema lacks, so the baseline of 3 is appropriate.

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 opens with a specific verb+resource: 'Переустановка ОС на существующем сервере' (reinstall OS on an existing server), which clearly distinguishes it from read-only list/status tools and power-control siblings. The parenthetical 'упрощённый путь через eq/order_instance' (simplified path via order_instance) additionally hints at a distinct mechanism from the create_reinstall_task sibling. An agent can tell what this tool does without opening the 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?

The description lists concrete prerequisites for invocation (HOSTKEY_ALLOW_DESTRUCTIVE=1, confirm=true, re-entering the current hostname), which gates when the call is permitted. However, it never explicitly routes the agent to an alternative (e.g., create_reinstall_task for the non-simplified reinstall path) or states when to prefer one over the other, so the 'simplified path' hint remains implied rather than actionable.

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