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

Beyond the annotations (readOnlyHint=false, idempotentHint=false), the description discloses the key behavioral trait: runs execute asynchronously and the response returns only a batchId, not results. It also tells the agent to follow llmContext guidance in results, which is useful non-obvious behavior. No contradiction with annotations exists.

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, each earning its place: the first states scope and limit, the second explains the async contract and follow-up tools, and the third adds an important instruction about result guidance. It is front-loaded and free of filler.

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 a rich input schema, an output schema present, and safety annotations available, the description adds exactly the missing contextual pieces: batch-size cap, async semantics, aggregation polling, individual-result retrieval, and llmContext handling. Nothing important needed for an agent to call and follow up on this tool 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 description coverage is 100%, so the schema already documents all five parameters, including constraints like maxItems, enums, and the exactly-one-of id/url/text requirement. The description adds little parameter-level meaning beyond framing inputs as 1-1000 documents and the processor as 'saved'. This is the expected baseline when the schema carries the full burden.

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 states a specific action (submit), a specific resource (batch of extract runs/extract group), and a specific target (a saved processor). It clearly distinguishes this batch tool from single-run operations such as extract_data and from sibling batch tools like run_parse_batch.

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 operational guidance: it explains that the call returns immediately, that execution is asynchronous, and that follow-up must be done via get_extract_batch and the extract-run list tool filtered by batchId. It does not explicitly name a single-run alternative or state when not to use this tool, but the batching and async framing sufficiently imply the intended usage.

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