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

Annotations already declare openWorldHint=true, idempotentHint=true, destructiveHint=false, so the burden is partly lifted. The description adds genuinely non-structured behavior: automatic JS rendering, robots.txt compliance, and tiered pricing with a cache discount. It does not explain the x402 payment handshake beyond what the schema says, so not a full 5.

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?

Three compact sentences, zero filler: purpose first, cost/behavior second, routing last. Every clause carries information an agent uses for selection or invocation.

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?

Output schema exists, so return values need not be described. Given the tool's complexity (payment, modes, caching), the description covers purpose, cost, behavioral traits, and sibling routing, leaving nothing critical to inference.

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 baseline is 3, but the description adds economic meaning to mode selection ('$0.005 fast / $0.01 rendered; cached results half price') and ties caching to cost, which the schema's ttl description does not. Minor friction: it says 'rendered' while the enum value is 'heavy', leaving the mapping implicit.

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 ('Extract a web page to clean Markdown + metadata') with the output artifact named. It explicitly carves itself out from structured_extract (schema filling) and pdf_info/parse_document (PDFs), so an agent can route without opening sibling schemas.

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?

Explicit selection rules: 'Choose this when you need a web PAGE as clean Markdown to read yourself', with named alternatives for the two nearest competing intents. Both the use case and the when-not conditions are stated.

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