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

Annotations only declare generic hints (readOnlyHint false, idempotentHint false, destructiveHint false), so the description carries the burden for nontrivial behavior. It discloses the non-blocking nature ('Returns a batchId immediately; runs execute async'), names the polling path, and mentions llmContext guidance in results. This adds real behavioral value without contradicting annotations.

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 no filler: the core submission capability, the async return behavior, and the result-retrieval path are each given one sentence. Key constraints and workflow are front-loaded, 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?

Given the high parameter complexity, the schema already covers parameter semantics fully, and an output schema covers return values. The description adds what is not derivable from the schema: async execution, immediate batchId, the polling tools to use, and the note to follow llmContext guidance. This makes the definition complete for an agent deciding to invoke it.

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 baseline is 3. The description's 'up to 1,000 documents' and 'saved processor' reflect schema facts already present in inputs.maxItems and processor, and it does not add meaning beyond the schema for parameters like environment, priority, or workspaceId.

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 and resource: 'Submit up to 1,000 documents as one batch of classify runs ... against a saved processor.' It is immediately distinguishable from sibling tools like classify_document and get_classify_batch while making the batch/async nature explicit.

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 follow-up usage guidance: 'poll aggregate status with get_classify_batch' and 'fetch individual results with the classify-run list tool filtered by batchId.' It does not explicitly contrast with single-run classify_document, so it misses an explicit when-not/alternative statement, but the intended workflow is clear.

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