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

Goes well past the annotations: discloses the exact price (0.012 USDC on Base), the x402 v2 payment-header handshake, that the caller must retry with identical arguments and idempotency key, the per-page 6,000-character cap, explicit partial-coverage reporting, and the key guarantee that no source is fetched before payment. That is exactly the auth/cost/side-effect context an agent needs before calling a paid, open-world tool.

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 constraints, then price, then payment mechanics — no filler sentences, and each clause carries actionable information. The payment sentence is a dense compound packing several facts ('canonical HTTP API resource'), which costs some readability.

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 and three required parameters, the description supplies pricing, payment protocol, limits, and a rough shape of the result (deduplicated, attributed, partial coverage explicit). Missing only failure/error and per-URL failure behavior, which is a minor gap for a paid extraction call.

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?

At 33% schema coverage the description must compensate, and it largely does: it adds the public-page restriction and URL count semantics for `urls`, ties the price to `max_amount_atomic` as a spending cap, and explains `idempotency_key` via the identical-arguments retry rule. It stops short of describing key reuse conflicts or uniqueness behavior, so not a 5.

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 (extract) and specific resources (main text, titles, metadata, links) scoped to 1–3 public HTTPS pages and a deduplicated, attributed result. The exclusion of web search and JS rendering sharpens scope, but no sibling is named, so the agent must infer why this beats xguard.web.fetch or xguard.fact.get.

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 clear when-not conditions (no JavaScript rendering, no private pages, no web search) and describes the retry path after a payment challenge. However, with five sibling tools it never names an alternative or the condition that routes to it, leaving tool selection to inference.

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