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

Beyond readOnlyHint/openWorldHint, the description discloses cost and rail ($0.01 per call over x402 at GET /v1/verdict), the integrity property that 'paying Lumi never changes a result', that on-chain payments are reported as ranges only, and a scope disclaimer ('Observations, not a guarantee'). These are exactly the behavioral traits annotations cannot convey, and they materially affect how an agent should interpret the output.

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 a single sprawling sentence chain with nested colons and parentheses, and it front-loads the price rather than what the tool does. The information is largely useful, but the structure makes it hard to scan and the label list competes with the usage guidance for attention.

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, and the description compensates well by enumerating the four labels and the accompanying fields (as-of date, evidence window, conclusive test-buy count, dates, reason codes, evidence and appeal links). With full schema coverage and rich behavioral disclosure, the remaining gap is minor: no mention of error/unknown-URL behavior or latency for a paid call.

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 description coverage is 100%, so all three parameters (url, payTo, amount) are already documented in the schema. The description only implicitly echoes the url parameter ('Before paying an x402 URL or seller domain') and adds no format, matching, or fallback semantics for payTo or amount. Baseline 3 is appropriate when the schema carries the parameter burden.

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 does state a specific verb+resource: a pre-payment check on an x402 URL or seller domain that returns one label from four enumerated values (checks_passed, check_first, checks_failed, no_data). It also distinguishes itself from siblings by naming lumi_trust_check and /v1/check as having the same data. The purpose is buried in a run-on sentence behind pricing, so it is clear but not cleanly front-loaded.

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 context is explicit: 'Before paying an x402 URL or seller domain', and it names alternatives with an ordering — 'the free lumi_trust_check and the free signed /v1/check have the same data, so try them first'. That is real when-to-use and when-not guidance. It stops short of 5 because the guidance sits inside a parenthetical and never explains the case where this tool is the right choice despite being paid.

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