web_read_batch

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

With no annotations, the description carries the full burden and does so: parallel fetching, per-page partial failure ('A failed page is reported with its error while the others still return'), conditional billing ('charged only if at least one page was read'), cost ($0.005 USDC per call) and p99 latency (9000ms). These are exactly the traits an agent needs to plan cost and error handling.

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 but zero waste: scope first, then alternatives, then failure/billing behaviour, then params, cost and latency. Every clause supplies information an agent would otherwise have to guess.

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?

No output schema exists, yet the description states the return format ('clean Markdown with title and description') and the failure shape. Combined with cost, latency, and size bounds, an agent has everything needed to invoke 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 description coverage is 100%, so the baseline is 3. The description restates both parameters with their bounds and default, adding little beyond the schema, and it introduces a minor inconsistency by saying '2 to 5 pages' while the schema and its own params line allow 1 to 5.

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 with scope ('Read 2 to 5 pages whose URLs you already know in one call') and immediately contrasts itself with web-scrape (one URL at a time) and web-scrape-batch (6-20 URLs). An agent can distinguish it from every neighbouring read/scrape sibling without opening a 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?

Explicit routing rules are given in both directions: 'for 6 to 20 URLs use web-scrape-batch' and 'To find URLs first, use site-map (one site) or search-read (a question)'. It also implies when not to use it, since it only handles URLs already known.

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