batch_create

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

Annotations only cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true); the description carries the operational load. It discloses the automatic-mode default, that forcing js_render/premium_proxy disables automatic mode for the affected tasks and bills them at that configuration's cost, that premium_proxy is 10x cost, and what BATCH_ACCESS_DENIED means. This is exactly the cost/auth context an agent needs before invoking.

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 purpose, then alternation/comparison, then billing semantics, then return values and error handling; every paragraph carries distinct information. Slightly dense and the cost/mode explanation is repeated for both js_render and premium_proxy, keeping it just short of a 5.

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 10-parameter, no-output-schema tool this covers what the schema cannot: the default automatic mode, the cost consequences of overrides, the return shape (job_id + latest_run.status/stats), the sibling tools for polling, and the access-denied failure mode. An agent has everything required to call it correctly on the first attempt.

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 the baseline is 3, but the description genuinely adds cross-parameter meaning: proxy_country works in automatic mode and requires premium_proxy when combined with js_render, and job-level vs per-task zenrows_params precedence. It does not restate the urls/tasks precedence rule already in the schema, which is the only real gap.

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?

Opens with a specific verb+resource+scope: 'Submit a cloud Batch job that fans out many URLs asynchronously (Zenrows Batch API).' It then explicitly distinguishes itself from the nearest sibling ('NOT the same as browser_batch') and from scrape/extract by workload size, so the agent can route without opening any 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 explicit when-to-use ('large URL lists') and when-not ('scrape and extract handle single pages'), names the sibling it is not (browser_batch) with the distinguishing endpoint and auth header, and points to batch_status/batch_wait/batch_results for the follow-on workflow.

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