Address Poisoning Check

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description repeats 'read-only' while adding genuinely new facts: 'free' and 'offline' (no network egress, so the address isn't leaked). Beyond that it describes the two checks performed but says nothing about the result shape or what a 'hit' looks like, which is the main behavioral gap.

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?

Two sentences, front-loaded with the safety guarantee and detection rule. The closing sentence is motivational rather than operational, but it does justify why an agent should prioritize the check, so it earns its place at a small cost.

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, the description should say what comes back — a boolean, a match list, a checksum-valid flag — and it does not, leaving an agent unable to interpret or act on the result. For a two-parameter verification tool that is the one material omission.

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 coverage is 100% and both parameters carry descriptions ('recipient you are about to pay', 'addresses you trust'), so the schema does the work. The prose clarifies the concept of the trust set ('address book, previous real payees') but adds no syntax, limits, or handling rules beyond the maxItems=50 already in the schema. Baseline 3 applies.

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 names a specific verb and resource ('check whether the recipient address is a lookalike ... and whether its EIP-55 checksum is valid') with the exact detection rule (same first/last hex characters, different middle). The only sibling, onchain_check_info, is never mentioned, so the agent gets no explicit differentiation between the two.

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?

Timing is stated precisely: 'before sending crypto,' which is a clear activation condition for an agent in a payment flow. There are no exclusions or named alternatives to contrast against, keeping this short of a 5.

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

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

Annotations only declare readOnlyHint=true; the description adds important behavior: it provides purchase information, the real check costs 0.005 USDC via x402, and this tool itself does not pay. It does not describe the response format, but the key safety and payment expectations are covered.

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?

Two short sentences, front-loaded with the purpose and immediately followed by the crucial non-payment caveat. Every phrase adds useful context about cost, protocol, networks, or behavior.

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 zero-parameter informational tool with a readOnly annotation and no output schema, the description covers what it informs about, the cost, supported networks, and non-payment. Minor gaps are the lack of explicit alternative routing to the sibling tool and no hint about the shape of the returned instructions.

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 tool has zero parameters, so the baseline is 4. There is no parameter-level information needed or missing.

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 that the tool explains how to buy an on-chain check, including the x402 protocol and 0.005 USDC price, and clarifies that it does not perform payment. It names the networks and scanned data, but does not explicitly distinguish itself from the sibling check_recipient_lookalike tool.

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?

Implies the tool should be used when an agent needs purchasing instructions rather than an actual check, reinforced by 'Does not pay.' It does not provide explicit when-not guidance or name the sibling alternative, so routing remains partly inferential.

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