sootool.policy_propose

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

Goes well beyond the annotations: discloses that the operation is non-effective ('아직 시행되지 않는다'), that it returns a 6-step validation report plus year-over-year deltas, that the draft expires at expires_at, and that a missing admin mode yields error=admin_required. These are exactly the auth, lifetime, and side-effect facts an agent needs for a write-flagged (readOnlyHint=false, idempotentHint=false) tool.

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, front-loaded with the admin marker and the core action, followed by return behavior, failure mode, and lifecycle. No filler and no restatement of the tool name.

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 the return-value description is a bonus, and the annotations plus admin/expiry guidance cover the behavioral side well. However, for a 10-parameter mutation tool with 0% schema description coverage, an agent still cannot tell what yaml_content must contain or what auto_fix_sha256 and sensitivity_threshold change — a real gap in the definition.

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% and the schema exposes only bare titles across 10 parameters, so the description carries the full burden — yet it names none of them. domain, year, yaml_content, notice_no, source_url, effective_date, auto_fix_sha256, and sensitivity_threshold are left completely unexplained; only '초안' faintly gestures at draft_id.

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 and resource ('정책 초안을 만든다' / creates a policy draft) and immediately separates it from the sibling that actually applies changes (sootool.policy_activate). The '[관리자]' prefix further scopes who may call it, so an agent can distinguish it from policy_validate, policy_diff, and policy_activate without opening any 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?

Gives a concrete precondition (SOOTOOL_ADMIN_MODE=1, otherwise error=admin_required) and names the alternative action for applying a draft (sootool.policy_activate). It does not explicitly say when to choose propose versus validate or diff, but the draft-vs-activate split covers the main routing decision.

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