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

With no annotations, the description carries the full burden and does well: it discloses the monetary cost per URL and per call ($0.015 USDC), the batch ceiling of 8, and the per-URL return fields (Markdown, title, word_count). It omits failure semantics — whether a failed URL aborts the batch or how partial results are billed — which is the main remaining behavioral gap.

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?

Dense and front-loaded: capability, cost, output shape, parameter format, total price, then alternatives. The per-URL price and the total price partially restate each other, and the 'Related:' line packs several ideas into fragments, but nothing is wasted.

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 single-parameter tool with no output schema and no annotations, the description covers purpose, cost, input encoding, output fields, limits, and sibling alternatives. The gap is error/partial-failure behavior and payment mechanics, which matter for an agent deciding whether to retry.

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?

The schema for 'urls' is an empty object with no type, no items, no description, so the description is the only source of format information — and it supplies exactly that ('comma-string or array'). This is essential disambiguation that the schema entirely lacks.

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 ('Batch web read'), the hard limit ('up to 8 URLs'), and the per-URL output shape, so an agent can immediately distinguish it from the single-page read_url sibling. The trailing 'Related:' clause explicitly separates it from /read and /convert.

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?

Routing guidance is present and concrete: use this for batching, /read for a single page, /convert for PDFs, with price deltas making the tradeoff explicit. It stops short of stating exclusions such as when a batch is a bad idea (e.g. one URL only, or more than 8 URLs), which keeps it off a 5.

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