Seven facts about an address before paying it (free)

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds real behavioral context beyond that: a 7-day Transfer-log window, per-fact value/evidence/method/measurement-time structure, and the explicit guarantee that an unavailable channel is reported rather than guessed. No permissions, latency or rate-limit detail is given, but for a read-only facts tool this is a solid addition.

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 definition is long and heavily semicolon-delimited, but it is front-loaded with the core purpose and every clause corresponds to a distinct fact, so little is padding. It reads as dense reference material rather than prose, which costs it the top mark but not much more.

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?

There is no output schema, so the description carries the return-shape burden and does so explicitly, stating that each fact carries value, evidence, method and measurement time and that unavailable channels are disclosed. Given the three-parameter read-only scope and the fact enumeration, an agent has everything needed to call and interpret it.

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, but the description goes further by explaining why the optional parameters exist: 'given the paying agent and the amount, whether it is a never-paid destination at a size the agent never sent' ties agent and amount_usd to two named per-agent facts. It also clarifies the payee is 'the 0x address to be paid', reinforcing the schema description.

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 states a specific verb+resource ('what the chain and our ledger say about an address an agent is about to pay') and enumerates the concrete fact set: code kind, delegate/sweeper shape, relay shape, swap outflow, funding/exit paths, claim-on-proof selector, issuer freeze, payer count, and two per-agent facts. An agent can tell this is an address-due-diligence tool and distinguish it from judgment-style siblings such as pay_check or counterparty_preview.

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?

Usage is implied by 'an address an agent is about to pay' and the title's 'before paying it', and the closing line 'Facts describe an address; they do not judge it' hints at the boundary with a verdict tool. However, no sibling is named and there is no explicit when-not-to-use or alternative-selection rule, so the agent must infer the routing.

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