sootool.policy_import

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

Goes well beyond the annotations: it discloses that the target store is overwritten (matching destructiveHint=true), that ed25519 signature verification is performed with an env-var switch, that failures surface as validation_failed, and that admin mode is a precondition. This is exactly the extra context annotations cannot carry.

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 purpose, then verification, then error behavior, then the admin prerequisite. Nothing is repeated from the schema and no sentence is 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?

For a destructive, non-idempotent mutation with an output schema already defined, it covers preconditions, verification path and failure mode. It could still note reversibility (policy_rollback exists) or whether the overwrite replaces the entire policy set, but no critical calling information is missing.

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 has to compensate: it explains require_signature, public_key_b64 and their interaction with SOOTOOL_POLICY_REQUIRE_SIGNATURE, plus the provenance of bundle. The bundle's nested content is left opaque (it is an untyped object with additionalProperties), which is the main remaining gap.

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 pair (verify then apply to overwrite repository) and a specific resource (bundle produced by sootool.policy_export). Naming the producing sibling makes it instantly distinguishable from policy_validate, policy_propose and policy_activate.

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 invocation context: the input must be a bundle from policy_export, admin mode is required, and signature is mandatory when the env flag is on. It does not say when to prefer policy_validate or policy_activate instead, so routing between the policy siblings is still partly left to inference.

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