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

Annotations already cover read-only, idempotency, non-destructiveness and open-world access, so the safety profile is not the description's burden. The description does add two genuinely non-structured traits: fail-closed denial semantics and a 0.012 USDC charge, which matter for an agent deciding whether to invoke a paid gate. It still omits what a denial looks like and whether the call is blocking.

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?

A single dense sentence with the most important trait ('fail-closed') front-loaded and no filler. It is efficient, though the semicolon-separated list of checks and trailing price make it read as a packed clause chain rather than clearly structured guidance.

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?

A paid, open-world, two-nested-object tool with no output schema and zero schema descriptions is significantly under-documented: the description never explains the shape of 'asset' or 'policy', what source_urls is for, or what the decision result contains. For the complexity indicated, this is not enough to call 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% and both required parameters ('asset', 'policy') are untyped nested objects, so the schema provides no semantics at all. The description lists the check categories (jurisdiction, KYC, allowlist, limit, transfer-window), which weakly hints at what 'policy' must contain, but never explains the asset object or the role of source_urls.

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 identifies the domain (RWA transfer compliance) and enumerates the check categories it covers, but the operative verb is only implied ('decision') and it gives no signal distinguishing it from siblings like rwa_transaction_assurance or transaction_assurance. An agent can guess its role but cannot confidently route between the overlapping RWA/assurance tools from this text alone.

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?

There is no explicit when-to-use statement, no prerequisites, and no named alternatives. 'Fail-closed' hints that it is a gate, but nothing tells the agent at which point in a transfer flow to call it versus rwa_sanctions_screening_evidence or payment_preflight.

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