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

annotations already cover the safety profile (readOnlyHint true, openWorldHint false), and the description still adds real behavioral value: per-call pricing ($0.05 USDC via x402), the 402-style handshake when unpaid, and the exact retry vectors (X-PAYMENT / PAYMENT-SIGNATURE headers or params._meta["x402/payment"]). It stops short of explaining what "authorized" means in practice (allowlist? domain restriction?) or what normalization the SHA-256 applies to.

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?

Front-loaded with the operation, then return values, then payment mechanics — a sensible order for an agent deciding whether to call. Every sentence carries payload; "No screenshot" is the only slightly cryptic fragment, though it usefully rules out a sibling capability.

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 only three flat parameters, no output schema, and annotations covering safety, the description supplies everything needed: what it does, what it returns, what it costs, and how to complete payment on retry. The only residual gap is behavior when neither prior-text parameter is supplied.

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 schema already documents all three parameters; baseline 3 applies. The description confirms that previousText and previousSha256 are alternative diff bases, but it never states whether one of the two is required or how conflicts are resolved, which is the one non-obvious thing about this schema (only url is marked required).

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?

"Diff an authorized page against a caller-supplied previous text or SHA-256" gives a specific verb (diff) and resource (page), plus an explicit list of what comes back (changed flag, new hash, token diff). The line "No screenshot" implicitly separates it from the page-fetch siblings like url_to_markdown, but no sibling is named outright, so an agent must infer the boundary.

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?

The word "authorized" signals a precondition and the x402 retry instructions describe a procedure, but nothing states when to pick this tool over url_to_markdown, page_structured_extract, or sitemap_to_markdown. Usage is implied by the diff framing rather than declared.

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