create_reinstall_task

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

The annotations already declare destructiveHint=true, so the agent knows it's destructive. The description adds a critical warning: 'ДЕСТРУКТИВНО: часть процесса, затирающего диски сервера' (destructive: part of the process that wipes server disks), which provides context beyond the annotation. However, it doesn't disclose other behavioral aspects like the need for confirmation (implicit in 'confirm' parameter) or any side effects beyond disk wiping. Given the annotation already flags destructiveness, the addition is modest, hence a 3.

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 concise: three sentences, with the key information front-loaded ('Шаг 1 PXE-переустановки...'). The destructive warning is clearly separated, and every sentence adds value. No filler or redundancy.

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 simple two-parameter tool with a clear workflow context, the description is quite complete: it explains what it returns ('reinstall_key'), how it fits into the reinstall process, and warns of destructiveness. It lacks details on prerequisites (e.g., server must be powered off?) or the full reinstall flow, but given the simplicity and schema richness, it's nearly sufficient. A 4 is warranted.

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 both parameters ('id' and 'confirm') are already documented in the schema. The description does not add any new information about the parameters themselves; it only implies via the destructive note why 'confirm' might be needed, but that's not explicit. Since the schema covers everything, baseline 3 applies.

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 the specific verb ('create'), the resource ('master key for reinstall'), and the context ('Step 1 of PXE reinstall'), and distinguishes it from sibling tools like 'reinstall_server' and 'check_task'. The key generated ('reinstall_key') is identified, and the relation to 'check_task' is explicit, making its purpose unambiguous.

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 implies usage as part of a reinstall workflow: it is the first step, and the key is used by 'check_task' to track stages. However, it does not explicitly state when not to use it or mention alternatives (e.g., 'reinstall_server'), leaving some room for an agent to confuse it with the higher-level reinstall operation. That said, the workflow context is clear enough for a competent agent.

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