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

Annotations already carry readOnly/idempotent safety, but the description adds genuinely non-obvious behavior: the call is paid (3000 sats or US$2.5 USDC), which is material to how an agent must sequence invocation. It also discloses the per-address plus flagged-summary return shape. It omits what happens if some addresses are invalid or how flagged results are prioritized.

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?

Three dense sentences, front-loaded with what is screened, then who it is for, then what it costs. No filler and the batch constraint appears in the opening clause.

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 does the necessary work of naming the per-address categories and the flagged summary, and it explains the paid-invocation flow that gates the call. It could be slightly stronger on failure handling or partial-batch behavior, but nothing essential for correct invocation is 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 25-item cap, the address formats, and the l402/pay_with payment parameters are all already documented in the schema. The description's 'up to 25' and price-per-call restate this rather than adding interpretation, so the baseline of 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?

States a specific verb and resource ('Screens up to 25 Bitcoin addresses in one call') and enumerates the exact risk categories returned (OFAC, ransomware lists, ownership clusters, sweeper bots, laundering patterns). It differentiates itself from the single-address sibling by referencing 'single checks' and the batch cap, though it never names bitcoin_address_risk or bitcoin_sanctions_screen 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?

Gives a concrete use context ('counterparty and withdrawal-address due diligence') and an economic reason to prefer this over single checks ('about 60% cheaper per address'). It stops short of stating when NOT to use it — e.g. for a single address, or when only a sanctions screen is wanted via bitcoin_sanctions_screen.

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