sootool.policy_export

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

Annotations already declare readOnly/idempotent/closed-world, and the description goes well beyond them: it discloses the output artifact's composition, that signing only happens when include_signature is true, that signing requires an ed25519 key file resolved through the SOOTOOL_POLICY_KEY_FILE environment variable with 0600 permissions, and which sibling accepts the bundle. This is exactly the kind of precondition/auth context annotations cannot convey, and it is consistent with readOnlyHint=true (export is a read).

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 purpose, then parameters, then the signing precondition, then the downstream consumer. No filler and no repetition of schema/annotation content.

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 explained, and annotations cover the safety profile; the description fills the remaining gaps (bundle format, signing setup, consumer tool). The one hole is the unspecified format/semantics of as_of and include_proposed, which matters for correct invocation.

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 carry parameter meaning; it assigns roles to five of six parameters (domain/name/year identify the policy, as_of/include_proposed select the version, include_signature toggles signing). However it never specifies the expected format of as_of (date string?) or what 'proposed' versions actually mean, leaving the agent to guess at call-time values.

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 ('정책 하나를 이식 가능한 묶음으로 내보낸다' — export one policy as a portable bundle) and immediately defines the bundle's contents (original YAML + metadata). This is clearly distinguishable from siblings like policy_get (fetch a policy) and policy_import (the named consumer of this output).

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 concrete selection guidance: identify the policy with domain/name/year, pick a version via as_of and include_proposed, and names sootool.policy_import as the tool that consumes the resulting bundle, which tells the agent the intended round-trip. It does not explicitly say when to prefer this over policy_get or policy_diff, so it stops just short of full when/when-not guidance.

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