Start a batch scrape

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

Annotations cover safety (readOnlyHint=false, destructiveHint=false, openWorldHint=true, idempotentHint=false), and the description adds genuinely new behavior: the job is asynchronous and returns only { taskId } immediately, invalid URLs are surfaced as invalidURLs when ignoreInvalidURLs is set, appendToId re-runs a completed batch, and idempotencyKey is retained 24 hours. The candid admission that result retention 'is not stated' is useful, though concurrency/rate-limit behavior is left unaddressed.

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 one-sentence purpose and return contract, then a workflow sentence, then parameter notes. Dense but essentially waste-free; the long middle sentence enumerating delegated scrape options is the only place readability suffers.

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?

An output schema exists, so the description need not explain return values, yet it usefully summarizes the immediate { taskId } response and the invalidURLs variant. For a 33-param, nested-object tool it covers purpose, async lifecycle, and the sibling chain adequately; the acknowledged gaps (result retention, quotas) are the remaining holes.

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?

With 33 parameters at only 42% schema description coverage, the description compensates by declaring the shared option set ('formats, onlyMainContent, includeTags, waitFor, timeout, verify, actions and the rest; their descriptions are on scrape'), which is the single most valuable thing it could say here. It also clarifies appendToId and idempotencyKey beyond their one-line schema text. Many parameters (maxAge, webhook, lockdown, maxConcurrency, robotsOverrides, includeSubdomains) remain undocumented in both places, so it is not exhaustive.

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+resource with scope: 'Run 1-1000 known URLs as one persistent job.' The word 'known' implicitly separates it from crawl-style discovery, and naming the sibling follow-ups (wait_batch, get_batch_items, get_batch_errors) pins down its place in the workflow. An agent can distinguish it from scrape and crawl 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?

Gives clear operational routing: use appendToId to add to an existing batch, idempotencyKey to make a retry safe, and the three named tools for waiting/paging/errors. It does not state when to prefer crawl or scrape_product instead, nor any exclusion (e.g. 'do not use for URLs you must discover'), so it stops short of a full when/when-not statement.

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