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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive hints. The description adds behavioral insight by clarifying the tool only uses caller-supplied facts and rules, and it exposes the x402 pricing ($0.002 per call). It doesn't explain error semantics or rate limits, but the low annotation bar is met.

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, front-loading the core purpose and then adding domain exclusions and a pricing note. The phrase 'trust identity permission / quality unknown' is slightly odd, but overall it is focused and economic.

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?

Given the tool's complexity—two nested parameters, an array up to 500 items, and no output schema—a single high-level mention of 'blocking violations and warnings' is insufficient. It lacks explanation of the output object shape, rule examples, or how severity/op semantics work, which an agent would need to reliably call the tool.

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 carry the weight. It gives only the top-level concepts 'facts' and 'rules' without explaining the key rule structure (field, op, value, message, severity) or how severity maps to blocking/warnings. This is insufficient for a caller to compose valid rules.

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 evaluator verb and resource ('Evaluates caller-supplied facts against explicit caller-supplied rules') and states the result ('blocking violations and warnings'). It also narrows the domain to 'trust identity permission' and excludes legal/identity/regulatory adjudication, which helps distinguish it from 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 gives a broad intended use ('Intended for trust identity permission / quality unknown') and an explicit negative list (legal, identity, sanctions, fraud, contractual, regulatory). However, it does not point to a specific alternative tool by name, so it stops short of the highest 'alternatives' guidance level.

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