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

With no annotations, the description carries the full burden and does it well: it discloses result ordering (results[] in input order), the partial-failure model (per-URL status ok/error with code and message), the billing rule ('charged once if at least one page is read'), and the $0.008 USDC x402 payment rails. These are exactly the traits an agent needs before committing a paid multi-fetch.

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 trigger sentence, then Input / Output / cost, each earning its place. The example query string conveys the space-separated format faster than prose would.

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 no annotations, the description covers purpose, input format, return shape, failure semantics, and pricing, which is nearly everything needed. The remaining gap is what the error codes can be and whether a partially failed batch is retryable.

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 baseline is 3; the description goes beyond it by stating the max_chars range (500-20000) that the schema only lists as a default, and by clarifying that flags=1 adds prompt-injection signals. It still does not explain what max_chars does if a page exceeds it (truncate vs error).

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 states a specific verb and resource (read a batch of URLs into clean Markdown) plus the hard scope limit of 1-5 URLs in one call. The 'all at once' framing makes it distinguishable from the single-URL siblings web_read and convert_to_markdown without opening either 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?

It gives a clear positive trigger: 'Use when an agent has several URLs (search results, citations)'. It does not explicitly say when to fall back to web_read / web_read_brief / convert_to_markdown for a single URL, so the exclusion is only implied by 'several'.

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