Split a document

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

With only openWorldHint in the annotations, the description carries the burden and does well: it discloses that split boundaries are AI-determined (non-deterministic), that the call blocks until the new document ids are available (so no get_job/wait_for_jobs polling is needed), and it quantifies cost at 0.2 credits per page rounded up. It omits whether the original document is retained or consumed, and any permission requirements.

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?

A single front-loaded sentence where each clause carries real information (action, mechanism, blocking behavior, price). The final clause 'and wait for the new document ids' is slightly awkwardly spliced but nothing is wasted.

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?

There is no output schema, and the description correctly states the return ('the new document ids'), plus cost and blocking semantics, which covers the main things an agent needs. Remaining gaps — fate of the source document and default dataset behavior — are minor for a 3-parameter tool.

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 67% — dataset and instructions are documented in the schema while document_id is bare — and the description only marginally compensates by clarifying that the document is an 'uploaded' one and that the AI decides boundaries (context for the instructions parameter). It adds no syntax, defaults, or format details beyond 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 names a specific verb and resource ('Split one uploaded document into sub-documents') and adds the mechanism ('AI deciding where each one starts'), which clearly separates it from siblings like extract, classify, or standardize. It never explicitly contrasts itself with those siblings, so it stops short of a 5.

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?

'one uploaded document' implies the prerequisite that the file must already exist via upload_document, but there is no explicit when-to-use/when-not guidance and no mention of alternatives such as extract for pulling data without splitting. Usage is implied rather than stated.

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