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

Annotations only cover the safety profile (readOnly, openWorld, non-destructive); the description adds substantial behavior beyond that: baseline-on-first-call, cursor advancement only on change ('nothing slips through between polls'), and critically the cost model ($0.003 USDC via x402 with an in-call payment requirement). Auth/payment prerequisites are disclosed, which is exactly the burden annotations do not carry.

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 core mechanic and cursor contract before expanding into use cases, params, pricing and a sample input. It is dense and the sentence mixing params, pricing and the sample is long, but essentially every clause earns its place; nothing is padded.

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 still explains the return payload ('added and removed lines of the page text, plus optional keyword alerts') and the cursor round-trip. It covers the loop contract, cost, payment, and parameters, so an agent has everything needed to invoke it correctly on the first and subsequent calls.

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 baseline is 3, but the description adds real value over the schema: 'keywords (list, alert when a keyword newly appears)', 'ignore ... e.g. timestamps or ads', and 'render (true for JavaScript pages)'. These examples clarify intended semantics (newly-appears, practical ignore cases) that the schema alone does not convey.

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+resource ('Website change monitoring') with a scoping mechanism that clearly distinguishes it from siblings like page_extract, page_summarize and web_scrape: it returns 'only what changed since your last call (added and removed lines of the page text)'. An agent can tell this apart from one-shot readers 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?

Explicitly frames the use case ('agents that check in a loop') and enumerates concrete targets (price pages, docs, changelogs, job boards, status pages, competitor sites, government notices), plus first-call vs. subsequent-call guidance. It stops short of naming an alternative (e.g. page_extract for a one-time read) or stating when NOT to use it, so it does not reach the explicit-alternatives bar.

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