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

Annotations already disclose readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds meaningful behavioral context beyond annotations: the tool is a paid resource with an explicit x402 price of $0.002 USD per call, and it only evaluates caller-supplied facts/rules rather than consulting external registries. No contradiction with annotations.

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 sentences with no filler. The primary action and input/output contract are front-loaded in the first sentence, followed by usage boundaries and cost. Every sentence earns its place.

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?

The description covers the overall contract, cost, and forbidden domains, and annotations cover safety/idempotency. However, with no output schema and no parameter semantics, the agent is left to infer how to format rules and what the returned violations/warnings look like, which is a notable gap for a rule-evaluation tool with nested parameters.

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 says 'caller-supplied facts against explicit caller-supplied rules,' which names the parameters but does not explain how rules should be structured, what operators mean, how severity maps to output, or what the `facts` object should contain. The schema provides structure but the description adds little semantic value for constructing a correct request.

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 ('Evaluates'), the exact resource ('caller-supplied facts against explicit caller-supplied rules'), and the outcome ('returns blocking violations and warnings'). It also narrows the intended domain to 'agent procurement / regulatory mismatch' and explicitly excludes legal, identity, sanctions, fraud, contractual, and regulatory adjudication, which helps distinguish it from the many sibling policy engines.

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 states both the intended use case ('Intended for agent procurement / regulatory mismatch') and clear negative boundaries ('Do not use for legal, identity, sanctions, fraud, contractual, or regulatory adjudication'). It does not name a specific sibling alternative to route to, so it stops short of a full 'use X instead' pattern, but the when/when-not guidance is strong.

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