Get batch errors

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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered. The description adds genuinely useful behavior beyond that: results span every attempt, are paginated at up to 1000 per page, and robotsBlocked carries robots.txt refusals while governance/SSRF refusals remain in errors — a subtle distinction an agent could not guess.

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?

Two sentences with no filler, and the purpose is front-loaded before pagination and return-shape detail. The second sentence is dense but each clause (page size, pagination keys, robotsBlocked carve-out) earns its place.

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 0% schema coverage, the description correctly compensates by enumerating the returned error fields and the robotsBlocked list. Minor gaps remain: no mention of ordering, retry linkage, or whether the list is cumulative across attempts vs current-only.

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 0%, so the description must carry parameter meaning. It explains cursor/limit as the pagination pair and states the page ceiling, which partially compensates, but never describes what id refers to (batch id) or whether cursor is opaque.

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: 'a batch's items that did not succeed, across every attempt.' The word 'errors' plus 'did not succeed' cleanly separates it from the success-oriented sibling get_batch_items and from get_crawl_errors (a different resource).

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?

No explicit when-to-use or when-not; the agent must infer that this is the failure-inspection call for a batch. It never names alternatives such as get_batch, get_batch_items, wait_batch, or cancel_batch, and gives no precondition (e.g., batch finished vs still running).

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