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

Annotations only flag openWorldHint/readOnlyHint=false; the description carries the real behavioral burden and does it well: $0.25 price, the exact PAYMENT-SIGNATURE header requirement, the five payment rails with amounts, the HTTP 402 challenge shape when unpaid, and the crucial guarantee that an unconfigured jury fails before payment so no charge occurs. The verdict computation (coherence = |sum(w*d)|/sum(w), weights 3/2/1) and the anti-hallucination substring gate are also disclosed. This is behavior an agent cannot infer from any structured field.

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 pricing is correctly front-loaded, but the sentence structure is a single sprawling parenthetical and the five payment rails are effectively enumerated twice (once in the price list, again in the 402 challenge). Tightening to state the price and header once would preserve all signal; as written, dense jargon like 'coherence-gated' and 'SML receiver' competes with the actionable instructions.

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?

For a paid, open-world tool with no output schema, the description covers the payment protocol, failure preconditions, and what the verdict consists of — enough to call it correctly. The remaining gap is the post-call story: it mentions a 'sealed stored receipt' but never says how the caller retrieves or references it, which matters given a dedicated receipt sibling.

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 the schema already documents claim, sources (max 8, HTTPS, fallback to web search under 2 usable), and sub_claims (max 4, sentence-split default). The description reinforces the decomposition behavior but adds no per-parameter syntax or formatting guidance beyond the schema. Baseline 3 is appropriate.

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 and resource ('Fact-check a claim against live web sources') and sketches the mechanism: sub-claim decomposition, live source fetching, juror entailment, coherence-gated verdict. That is clearly distinguishable from fact_check_receipt or fact_check_methodology by name alone. It stops short of explicitly contrasting itself with the preview/status siblings, so not a 5.

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 only implied: you call it when you have a claim to verify, and the description notes a precondition (jury must be configured or the call fails before payment). There is no explicit routing to siblings — nothing says to run fact_check_preview first to see cost, or to use fact_check_status/receipt afterward, even though the tool mints a 'stored receipt' that a sibling presumably retrieves.

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