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

Goes well past the annotations (readOnly/openWorld/not-idempotent/not-destructive): it never pays or signs anything, it performs exactly one anonymous GET, unpaid calls cost nothing, and the failure mode is an isError with a fresh invoiceId. That tells the agent what happens on both the success and payment-required paths, which the annotations alone cannot.

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 answer is front-loaded with pricing boilerplate that partly duplicates the title, and 'Pay per call' plus 'Unpaid calls cost nothing' restate the same fact. Once past that, sentences are dense but carry real information, so it is adequate rather than tight.

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 takes on the job of describing return values and does: raw advertised fields as received, plus source and observed_at, and an isError PaymentRequired object with a fresh invoiceId when unpaid. Only the exact shape of the returned envelope is left implicit.

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 both url and payment_signature are already documented, giving a baseline of 3. The description adds the useful sequencing context that payment_signature should be omitted on the first call and that _meta["x402/payment"] is an equivalent channel, but adds no format or encoding detail beyond the schema.

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: the raw x402 payment-required fields (header and/or JSON body) a URL advertises to one anonymous GET, returned with source and observed_at. The framing line 'solves one question: What payment terms does this URL advertise in its x402 response?' lets an agent separate it from siblings like get_x402_activity or get_x402_health_report without opening any schema.

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 concrete operating conditions: public http(s) URLs only, one anonymous GET, no safety/price/seller verdict, and the full two-step flow (first call returns isError with PaymentRequired, retry with a signed payload via _meta or payment_signature). It does not point at any named alternative tool for related questions, which is the only gap.

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