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

Annotations already cover the read-only, open-world, idempotent, non-destructive profile, and the description adds materially more: the x402 payment flow ($0.002 USDC on Base or Solana via X-PAYMENT), the alternative prepaid credit key via Authorization: Bearer xs_..., and the fact that it is not in the free trial. The per-page pricing tied to the requested limit is an important cost behavior an agent must know before calling.

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?

It is one dense sentence, front-loaded with the action, and every clause (scope, return format, price, payment mechanism, trial exclusion) carries information. The heavy em-dash packing makes it slightly harder to scan than a clean two-sentence split would be.

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?

For a four-parameter, no-output-schema tool, the description covers scope, return type, cost, and authentication, which is what an agent needs to call it correctly. It omits operational edge cases such as robots.txt handling, deduplication, or partial-failure behavior during a crawl.

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 all four parameters (url, limit, include, maxChars) are already documented, including the 1-50 range and the charge-on-limit caveat. The description only restates the pricing-per-limit point and adds no new meaning for include or maxChars, so the baseline 3 applies.

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 names a specific verb and resource ('crawl a website') plus the traversal strategy ('breadth-first from a start URL on the same host') and the return format ('clean markdown for up to 50 pages'). That distinguishes it in practice from extract or map_site, but no sibling is named explicitly, so differentiation is left to inference.

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?

Usage is implied by the scope statement (same-host, breadth-first, up to 50 pages) and by the pricing/access notes, but there is no explicit 'use this when... instead of extract/map_site' guidance or any stated exclusion beyond the free trial.

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