execute_recovery

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

With no annotations provided, the description carries the full transparency burden and does it well: it lists exact side effects such as 'Deep prune of unused containers, networks, images, and volumes', 'Terminates a runaway process by PID', and 'Truncates journal logs to limit'. It also discloses the return format including 'security error'. It stops short of stating irreversibility or potential service-impact severity, which keeps it from a 5.

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 front-loaded with the primary purpose and then organized into a compact bullet list, an Args section, and a Returns section. Every sentence carries meaningful information; the length is justified by the number of actions described. No filler or repetition.

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 complexity, the output schema presence, and the absence of annotations, the description covers all actions, their target semantics, and the return shape. It could additionally note prerequisites like root permissions or the fact that several actions are irreversible, but the current text is sufficiently complete for an agent to invoke the tool correctly.

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%, so the description must fully compensate. It does so by enumerating every allowed action_name value with concrete target requirements and examples such as target='nginx' and target='12345'. This is far more informative than the schema's bare strings and gives an agent everything needed to construct valid calls.

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 and resource: 'Execute an emergency recovery operation from a strictly whitelisted list.' It clearly differentiates itself from the read-only diagnostic sibling tools such as check_service_status and analyze_disk_usage by framing this as a recovery/action tool. The bullet-list of allowed actions makes 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 phrase 'emergency recovery operation' establishes clear context for when this tool is appropriate, and the 'strictly whitelisted' phrasing imposes a strong constraint against arbitrary actions. It does not name sibling alternatives or explicitly say when not to use them, but the contrast with the read-only sibling names is evident. The per-action target requirements also give concrete operational guidance.

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