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

Goes well past the annotations: parallel fetching, per-page failure isolation via 'statuses with its reason and the rest still answer', a static-only limitation, a 20,000 character per-page ceiling, and a full cost model ($0.01/call, first 25 free, failed calls free, repeats not free). The charging note independently explains why idempotentHint is false, which the annotation alone would not convey.

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 verb, resource and return contents, and no sentence is filler. The billing and safety clauses are crammed into long semicolon-chained sentences at the end, which slightly hurts scannability.

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 carries the return contract and does it: field names (text/Markdown, title, author, published date), the statuses array and its per-page reason semantics, and the truncated-length limit. Combined with the static-only caveat and cost, an agent has everything needed to call this correctly.

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 real value: it frames urls as 'the request shape search APIs use (urls as a list)' and supplies a concrete example call, clarifying the one-to-five and multi-URL semantics. It does mention the 20,000 cap without the 4000 default, so the maxChars default still only comes from the schema.

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 ('Read one to five public web pages in one call') plus exactly what is returned: clean text or Markdown, title, author, published date. It is clearly separable from siblings such as search (which finds URLs), html_to_text (which converts provided markup) and extract_rendered (which implies JS rendering), because it declares 'Static HTML, Markdown and plain text'.

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 a concrete usage cue, 'Use to read search results in one call', which tells the agent when to reach for this over repeated single-URL fetching. It stops short of naming alternatives or exclusions (e.g. what to use for JS-rendered pages or for already-fetched HTML), so routing for edge cases is left to inference.

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