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

Annotations cover safety, but the description adds important context beyond them: the result is heuristic not proof, it draws from this node's last 30 days of logged cases, and the call is paid (50 sats or US$0.05 USDC). These details materially affect interpretation and invocation.

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 front-loaded with purpose and packs useful details into one dense sentence. It is efficient and every clause adds value, though the long sentence could be split for easier scanning.

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 explains what is returned (score, level, rules fired, or a clear no-case). It also covers data provenance, time window, heuristic caveat, and payment cost. Together with annotations, an agent has enough to call and interpret the tool correctly.

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 all three parameters are documented in the input schema. The description does not add meaning beyond what the schema provides for txid, pay_with, or l402; it only mentions the call price in passing.

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 clear verb-resource pair: AML check for one Bitcoin transaction. It also specifies the output shape (score, level, rules fired) and the scope (single transaction). It distinguishes by scope from address-level and batch siblings, but doesn't name those alternatives explicitly.

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 single-transaction scope and 'Heuristic, not proof' caveat imply when to use it, but there is no explicit when-to-use or when-not guidance, nor are alternatives like bitcoin_address_risk or bitcoin_aml_live named. Usage is only inferred.

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