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

The description goes beyond the annotations by disclosing that runs execute asynchronously and that a batchId is returned immediately. This is important behavioral context the annotations do not convey. It does not contradict the readOnlyHint=false or idempotentHint=false annotations, and it aligns with the non-idempotent batch-submission nature.

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 dense sentences carry all essential information: what the tool does, the batch limit, the async behavior, and the follow-up workflow. There is no filler or redundancy; the key constraint and guidance are front-loaded.

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 an async batch tool with a rich schema and output schema, the description provides the missing operational context: immediate batchId return, polling via get_split_batch, and retrieving individual results by batchId. An agent has enough guidance to invoke the tool and continue the workflow 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?

Since schema description coverage is 100%, the baseline is 3 and the schema already documents all parameters thoroughly. The description adds little parameter-level semantics beyond restating the batch limit and saved processor concept, which are already present in the schema.

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?

The description clearly states a specific action ('Submit up to 1,000 documents as one batch of split runs'), the target resource ('a saved processor'), and the async return mode. It is easy to distinguish from sibling run_*_batch tools because it explicitly names 'split runs' and the batch submission pattern.

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?

The description gives clear context for when this tool is appropriate: submitting a large batch of split runs against a saved processor. It also provides concrete follow-up usage guidance by naming get_split_batch for polling and a split-run list tool filtered by batchId for results, though it does not explicitly contrast with single-document alternatives like split_document.

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