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

Annotations already declare readOnly/idempotent/closed-world, but the description adds substantial behavior beyond them: exact pricing ('$0.008 USDC per call via x402 on Base'), the honest-answer billing nuance ('observed-unchanged ... is a real answer and is billed'), the no-verdict policy for `not_observed` with its rationale, and the watermark semantic that it is 'the last date MCPFax actually observed, never the current clock' so no window is skipped. No contradiction with annotations.

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 description is roughly 150 words, well above typical length, but nearly every sentence earns its place: scope, anti-discovery disclaimers, call pattern, differential-return semantics, billing, and the not_observed caveat each carry distinct information. It is front-loaded with the core purpose before caveats, and the density is justified by the domain complexity.

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 carries the burden of setting response expectations, and it names the key response elements: changes after the watermark, a fresh watermark, observed-unchanged entries with dates, the not_observed list with no verdict, and archive span. It also covers billing and the first-call archive behavior via schema. The remaining gap is the precise structure of an individual change record, which an agent would need to reliably parse results.

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; the description still adds real meaning to both parameters. It explains that `subjects` is limited to 50 and how the `since` watermark drives differential results, and it deepens the watermark contract (observation date, not current clock). The schema already documented first-call behavior ('Omit on a first call to receive the whole archive'), so the description complements rather than replaces it.

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 purpose: detecting changes (payTo rotations, price, asset/network, terms, tool-schema) under an x402 endpoint or MCP server that is ALREADY integrated. It explicitly disclaims what it is not ('not a discovery tool and will not help you choose a server'), which distinguishes it sharply from siblings like preflight_check and the scoring tools.

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?

It gives clear when-to-use context ('the one you wired in still matches what you wired in') and a strong when-not exclusion ('will not help you choose a server'). The call pattern for repeat checks is explicit: pass up to 50 subjects plus the `since` watermark to keep checks cheap. It does not name a specific sibling tool to use instead for discovery, which is the only gap preventing a 5.

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