sootool.policy_rollback

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

Goes well beyond the annotations by disclosing what is destroyed (the override version file), the ambiguity failure mode (ambiguous_version when effective_date is omitted), and the no-op outcome (rolled_back=false), which also implies non-idempotency consistent with idempotentHint=false. It lacks detail on recoverability of the deleted file or scope of admin auth.

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?

Four short sentences, a front-loaded [관리자] tag, and each sentence adds a distinct fact (action, disambiguation, no-op result, prerequisite) with no repetition of the schema.

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?

An output schema exists, so return-value explanation is not required, and the destructive/ambiguous behavior is covered. However, for a destructive mutation with 0% parameter documentation, leaving `domain` and `name` completely unexplained is a meaningful gap.

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 coverage is 0%, so the description carries the full burden. It explains effective_date's YYYY-MM-DD format, its optionality and the ambiguous_version consequence, and ties year to version selection, but never explains what `domain` or `name` identify — half the parameters remain undefined anywhere.

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?

States a specific verb+resource (delete the policy version file in the override store to revert to package defaults) and is clearly distinct from siblings like policy_activate or policy_propose. It does not name a sibling alternative explicitly, so it stops just short of a 5.

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?

Gives clear conditions for use: reverting an override to package default, admin mode required, effective_date needed when multiple versions exist in the same year. No explicit when-not guidance or named alternatives, so not a 5.

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