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

Annotations already declare this a mutating, non-idempotent, open-world operation; the description adds the most important trait beyond them — runs execute asynchronously and only a batchId is returned immediately. It also discloses the non-obvious instruction to follow any llmContext guidance included in results, which annotations cannot express.

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?

Three sentences with zero filler: the core action, the async follow-up workflow, and the llmContext caveat. The purpose is front-loaded before orchestration details, and every sentence 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 an output schema present and full parameter documentation, the description correctly targets what is not in the schema: the async contract, the polling route, and result-handling guidance. Edge cases like rate limits, quotas, or failure behavior are unmentioned, but nothing necessary for a correct first call is missing.

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% and the schema already documents each parameter in depth (exactly-one id/url, processor version semantics, environment enum with get_me note, workspace constraints). The description only restates the 1,000-document cap already present as maxItems, adding no new parameter-level meaning.

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 (submit) plus resource (batch of split runs against a saved processor) and scope (up to 1,000 documents). The async-execution qualifier and parenthetical (split group) clearly separate it from sibling batch tools like run_parse_batch and run_classify_batch, and from single-run split_document.

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 a concrete orchestration contract: returns batchId immediately, execute async, poll get_split_batch, fetch individual results via the split-run list tool filtered by batchId. However, it never explicitly names alternatives or states when not to use it (e.g., for a single document), so exclusions are absent.

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