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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false. The description adds valuable behavioral context beyond those: the evaluation semantics (facts vs. rules), the output type (violations and warnings), and the paid nature with a specific price. It does not contradict annotations, and the pricing disclosure is material for agent invocation.

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 compact at three sentences and front-loads the core behavior. The exclusion list and pricing information are useful additions. The phrase 'quality unknown' is awkward and slightly undermines clarity, but it does not waste substantial space.

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 policy engine with nested objects and no output schema, the description gives enough to grasp the basic contract: evaluate facts against rules, get violations/warnings. It does not specify the structure of returned violations, how blocking vs. warning outcomes manifest, or what valid facts look like. The rich rule schema compensates for some of this, so the overall definition is minimally viable but has clear gaps.

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 compensate for explaining facts and rules. It only restates the parameter names at a high level ('caller-supplied facts against explicit caller-supplied rules') without explaining what a fact object should contain, how rule operators behave, or how severity affects output. The schema itself is detailed, but the description adds almost no semantic clarity over it.

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 opens with a specific verb, 'Evaluates', a resource ('caller-supplied facts against explicit caller-supplied rules'), and a clear output ('blocking violations and warnings'). It also enumerates excluded domains, which sharpens what the tool is for. However, it does not distinguish this policy engine from the many other trust_identity_permission_policy_engine siblings, so differentiation is partial.

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?

The description provides a clear domain context ('trust identity permission') and explicit negative exclusions ('Do not use for legal, identity, sanctions, fraud, contractual, or regulatory adjudication'). It lacks positive routing to specific alternatives among the numerous sibling policy engines, so when-to-use vs. other engines is only implied by the domain label rather than explicitly contrasted.

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