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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, so the description correctly avoids repeating those. It adds value by disclosing the cost ('Paid resource; x402 price is $0.002 USD per call') and the output nature ('returns blocking violations and warnings'), which are behavioral facts not covered by 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 concise sentences: the first states the function, the second gives exclusions and intent, and the third covers cost. Every sentence carries useful information with no filler or repetition.

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 is reasonably complete for a read-only, idempotent tool, but it lacks details on the return format (no output schema exists) and leaves 'quality unknown' ambiguous. It also does not clarify how the 'severity' field influences blocking vs. warning behavior, though the schema partly covers this via enums.

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 the lack of parameter documentation. It only names 'facts' and 'rules' without explaining their structure, expected values, or how they relate, leaving the agent to infer semantics from the raw schema. The rules schema has nested properties and enums that remain unexplained in the description.

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 and object: 'Evaluates caller-supplied facts against explicit caller-supplied rules and returns blocking violations and warnings.' This clearly states the operation and distinguishes it from more general policy engines, though it does not explicitly differentiate from the version-less sibling 'execution_safety_preflight' or explain the '8ce15b25' suffix.

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 gives a clear negative boundary—'Do not use for legal, identity, sanctions, fraud, contractual, or regulatory adjudication'—and implies a preflight safety context with 'Intended for execution safety / quality unknown.' However, it doesn't specify when to use this tool over the many similar siblings (e.g., policy engines, verification tools), nor does it provide positive use-case examples.

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