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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, so the bar is lower. The description adds genuinely new operational behavior: $0.12 pricing, x-credit-token header for unlimited calls, free daily call, no wallet/API key requirement, and the synthesized verdict format. No contradiction with 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?

Purpose is front-loaded in the first clause, and subsequent sentences justify themselves with output details, pricing, and access constraints. Minor marketing filler like 'agent-ready intelligence you can't get free' is acceptable and does not bloat the definition.

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 one-parameter tool with a rich output schema and safety annotations, this is complete: it specifies the input, the synthesized output scale, network, pricing, and authentication model. An agent can correctly select and call it without needing to consult another tool's description.

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 single address parameter is fully described in the schema at 100% coverage, so the baseline 3 applies. The description adds the Base-network context and says the input is required, but does not add format, checksum, or example syntax beyond what the schema already provides.

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?

States a specific deliverable ('AI-written due-diligence verdict'), the target resource (Base token), the aggregated signals (risk, holder concentration, price/liquidity, OFAC), and the output scale (avoid → favorable). This differentiates it from single-signal sibling tools like token_risk or sanctions while making its scope unambiguous.

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 conveys when to use it via 'flagship report' and 'one call' as an umbrella due-diligence step, but it never states explicit alternatives, exclusions, or 'use X instead'. The context is clear enough to imply use for initial token due diligence, but not formally routed against siblings.

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