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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the bar is lower, yet the description still adds real substance: the allow/review/block outcome vocabulary, the concrete risk categories checked (sanctions, malicious tokens, address poisoning, first-time payee), and a plan prerequisite ("Builder plan and above"). It does not cover latency, rate limits, or coverage boundaries of the screening data, keeping it off a 5.

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 purpose and return shape are front-loaded in the first sentence, risk categories in the second, and the applicability/prerequisite notes last. Every sentence carries distinct information with no repetition of the name or annotations.

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?

With no output schema present, the description compensates by naming the verdict values and their reasons, and it adds a plan-tier prerequisite. For a 5-parameter read-only screening tool, an agent has enough to decide to call it and interpret the result without opening anything else.

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 80%, so the baseline is 3, and the description rises above it by embedding from/to/asset/amount into a single natural-language question that makes their roles obvious (sender, recipient, the amount of that specific asset). The `chain` parameter is never referenced in the description, leaving it to the schema alone.

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 gives a precise verb and resource ("pre-signature transfer check (payment screening)") plus the exact question it answers, so an agent knows this evaluates a specific transfer rather than an entity or wallet. It implicitly separates itself from post-hoc siblings like analyze_transaction via "Works before the transaction exists," but it never names screen_wallet, screen_entity, or screen_transfers_batch, so sibling differentiation is inferred rather than stated.

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?

"Use in wallet, custody, payment and treasury flows" gives a context of use, and "Works before the transaction exists; no chain lookup needed" implies it should be chosen pre-broadcast. There is no explicit when-not guidance or routing to alternatives (e.g., wallet-level screening or the batch variant), so selection still requires inference.

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