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

With readOnlyHint, openWorldHint, and idempotentHint already in annotations, the description adds useful behavioral context above the annotations: it lists the screening sources, the outputs are explained as receipts rather than a black-box, and it discloses supported but distinct address families. It thoroughly states what the tool does not hide or normalize, and no contradictions with the annotations exist.

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 efficient and front-loaded: it opens with 'Run an AML compliance screen' then quickly covers raison d'être, data sources, purpose, output format, and free accessibility. Every sentence carries distinct information, though it is slightly richer than strictly necessary, so a near-top mark feels appropriate.

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 gives a robust map of outputs (verdict, risk score, blocked flag, matching signals) and catches supported chains (EVM, Tron, Solana). It lacks such as timeout bounds, error handling for invalid addresses, or a note about non-determinism, but given the tool's surface area, the essentials are completely present.

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?

The input schema has 100% coverage for both parameters, so the baseline for parameter noise is already filled. The description adds supporting mention of EVM/Tron/Solana address patterns, confirming that address semantics are respected across chains, but it mostly restates what the schema already offers, so it adds marginal but non-essential semantic value.

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 by clearly stating the tool's function: run an AML compliance screen on a single blockchain address before payment, and frames it as an answer to a concrete safety question. It adds scoping ('single address'), which contrasts with the sibling tool recent_flagged, and lists exact inputs/outputs, all with a clear action and target resource.

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 strong guidance on when to use the tool ('BEFORE paying or receiving from it') and clarifies the kind of decision support it provides. It does not explicitly name the sibling tool as an alternative for multi-address/list-based checks, so it lacks a strict exclusions-by-sibling reference, but the context is unambiguous.

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