Free address-poisoning lookup (Base or Ethereum)

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

Annotations only cover read-only/open-world/idempotent, and the description adds substantial context beyond that: no wallet or payment required, per-IP rate limits of 30/min and 500/day, unchanged JSON passthrough, and the crucial staleness semantics of Ethereum data_through. It also discloses scope limits (poisoning only, no sanctions or scam lists), which is exactly the behavioral framing an agent needs before trusting a false negative.

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?

Front-loaded with the highest-value qualifier ('Free (no wallet, nothing paid)') and organized as purpose, return shape, interpretation, alternatives, limits. It is a dense single block with heavy parenthetical nesting, which costs a little scannability, but no sentence is filler.

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?

No output schema exists, yet the description names the returned fields (flagged, first_seen, kind, data_through, coverage) and explains how to interpret each, including the false-negative trap. For a two-parameter read tool this leaves nothing an agent needs missing.

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%, so the baseline is 3; the description still adds value by contrasting 'base (default, live)' against 'ethereum (daily scan, not live)' and by imposing a checksum requirement for mixed-case addresses that the schema pattern alone does not convey. It stops short of adding format examples or guidance on when to prefer one chain.

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 verb and resource: look up whether the address-poisoning watcher has flagged an EVM address as a lookalike or poisoning bait, with named chain scope. It explicitly separates itself from the sibling risk tools, so an agent can route correctly without opening any schema.

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?

Gives explicit when-to-use (pre-send check of the recipient) and when-not-to-use ('flagged=false is NOT a safety verdict'), naming the alternatives check_address_risk_lite and check_address_risk_quick for a full pre-send screen. The Ethereum caveat ('a DAILY scan, not live') is a usage condition, not just a fact.

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