sootool.policy_activate

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

Beyond the annotations, the description discloses concrete behavior: it overwrites stored state, clears the cache, writes an audit record, and deletes the draft after applying it. That is meaningful context for a destructive, non-idempotent operation, though it stops short of saying whether the overwrite can be undone other than via rollback.

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 three dense sentences that front-load the admin qualifier and the main effect, then add the failure modes and the deletion side effect. There is no filler.

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 values need not be described. Together with the annotations and the error-code disclosure, the description covers what an agent needs for a destructive admin mutation; the only remaining gap is detail about the draft_id parameter.

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?

There is a single parameter with 0% schema description coverage, so the description must explain draft_id. It only implies that it refers to a validated draft; it does not state the identifier's format or where to obtain it (for example, from policy_list or policy_propose).

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 names a specific verb and resource ('검증을 통과한 초안을 덮어쓰기 저장소에 반영') and marks it as admin-only, which is enough to distinguish it from siblings such as policy_validate or policy_rollback. It never names those siblings explicitly, so the differentiation is left implicit.

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?

It spells out two preconditions for use: the draft must have passed validation and the caller must be in admin mode, with the exact failure codes (validation_failed, admin_required). It gives clear context but does not explicitly exclude or compare against alternatives such as policy_rollback or policy_propose.

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