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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context beyond annotations: it returns blocking violations and warnings, it evaluates caller-supplied facts against caller-supplied rules, and it is a paid resource with a specific price. It does not contradict 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?

Three sentences with no filler. The core behavior is front-loaded, the intended use and exclusions follow, and the pricing note is a single compact clause. 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?

For a two-parameter tool with no output schema, the description covers the input semantics, the output type (blocking violations and warnings), the intended domain, exclusions, and cost. It does not describe the exact return structure, but with no output schema and a simple violations/warnings result, the description is sufficiently complete for an agent to select and invoke the tool correctly.

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 carries the burden for parameter meaning. The description explains the high-level roles of the two parameters ('caller-supplied facts' and 'explicit caller-supplied rules') and the output concept ('blocking violations and warnings'), which maps to the severity enum in the rules schema. However, it does not detail the facts object shape, the rule field/op semantics, or the message/severity fields beyond what the schema already shows. Baseline 3 is appropriate because the description adds some semantic framing but the schema still does most of the parameter-level work.

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 states a specific verb ('Evaluates'), a clear resource ('caller-supplied facts against explicit caller-supplied rules'), and a concrete outcome ('returns blocking violations and warnings'). It also names the intended domain ('trust identity permission / permission mismatch') and explicitly excludes adjacent domains, which distinguishes 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 explicitly says when to use it ('Intended for trust identity permission / permission mismatch') and when not to use it ('Do not use for legal, identity, sanctions, fraud, contractual, or regulatory adjudication'). It also discloses the paid nature and exact price, which is a practical usage constraint. This is strong routing guidance.

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