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

The description discloses that runs execute asynchronously, returning a batchId immediately, and provides the exact polling and result-fetching mechanism. This goes beyond the annotations (readOnlyHint false, openWorldHint true, idempotent false) by revealing the async execution pattern and the need to poll. It does not contradict any annotation.

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 sentences front-load the core purpose and then give the essential async follow-up. Every clause carries information: batch size, resource, immediate return, async execution, and specific next steps. No 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?

Given the tool's complexity (5 parameters, nested objects, output schema), the description is complete: it explains the async behavior and precisely names the poll and list tools. The output schema handles return values, so no further return-format detail is needed. The only minor omission is an explicit mention of the single-document alternative, which is more a usage-guidelines concern.

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?

The input schema has 100% description coverage, so every parameter (inputs, processor, environment, workspaceId, priority) is already documented with descriptions and constraints. The description adds only a restatement of the batch size ('up to 1,000 documents') and 'saved processor,' which are already in the schema. Per the baseline rule for high schema coverage, this warrants a 3.

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 opens with a specific verb and resource: 'Submit up to 1,000 documents as one batch of extract runs (extract group) against a saved processor.' This clearly differentiates it from single-run tools like extract_data and from other batch tools (run_classify_batch, etc.) by naming the resource type and batch size. The title complements the description without becoming a tautology.

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 tells the agent to use this tool to submit multiple documents as a batch and immediately provides the follow-up workflow: poll with get_extract_batch (wait: true) and fetch individual results with the extract-run list tool filtered by batchId. This gives clear context on when to invoke it (when a batch of extractions is needed) but does not explicitly name the single-document alternative (extract_data) or state when not to use it. The absence of an explicit exclusion drops it from a 5, but the guidance is still actionable.

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