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

Annotations only indicate readOnlyHint=false, idempotentHint=false, etc., which are generic. The description adds critical behavioral traits: returns a batchId immediately, runs execute asynchronously, and describes the polling and result-fetching workflow. This goes well beyond what annotations convey.

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 with no redundancy. The core action and size limit are front-loaded in the first sentence, and the async workflow is appended in the second. Every sentence earns its place, and the structure leads with the most important information.

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 rich input schema and the presence of an output schema, the description covers the essential operational context: submission, size limit, async behavior, and how to track results. The only notable gap is the vague phrase 'the classify-run list tool' instead of naming list_classify_runs, which is a minor friction point.

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%, with rich property descriptions (e.g., 'Exactly one of id/url/text', 'Must match a granted target from get_me'). The description adds no new parameter semantics beyond restating the 1-1000 document limit already present in the schema's maxItems/minItems.

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 ('Submit'), specifies the resource ('batch of classify runs'), quantifies the limit ('up to 1,000 documents'), and names the target ('saved processor'). This clearly distinguishes it from single-run tools like classify_document and other batch tools such as run_extract_batch, even without explicitly naming them.

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 implies batching multiple documents and gives explicit follow-up guidance: poll get_classify_batch with wait:true and fetch results via the classify-run list tool filtered by batchId. It does not explicitly name classify_document as the alternative for single runs, but the context of 'up to 1,000 documents as one batch' provides sufficient usage signal.

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