upload_document

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

With no annotations provided, the description carries the full disclosure burden. It reveals the asynchronous behavior, OCR processing, and the fact that the return value is a task ID. It does not mention error cases, file size limits, or whether the upload is immediately searchable, but the core behavioral trait is clearly disclosed.

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?

The description is short and front-loaded with the main purpose, then provides the most important parameter detail and the async return behavior. It wastes no words, though the omitted parameter documentation prevents a perfect score because some of the compactness comes at the expense of completeness.

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?

The description explains the return value and async behavior but does not cover five of seven parameters. Since there is no output schema and no annotations, the description is the only source of context, and its incomplete parameter coverage leaves an agent uncertain about optional metadata fields and the create_missing behavior.

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 0%, so the description must compensate. It documents only file_path and created, adding useful meaning for those two parameters, but leaves tags, title, correspondent, document_type, and create_missing completely unexplained beyond their raw schema names and defaults. This is a significant gap for a 7-parameter tool.

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 clear verb and resource: 'Upload a file to Paperless.' It also specifies that the tool returns a task ID and that processing/OCR are asynchronous, which immediately distinguishes it from the sibling search, retrieval, listing, and update tools.

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 the usage context clearly: use this tool to ingest a local PDF/image file into Paperless. It explains that processing runs in the background, so callers know to expect a task ID rather than an immediate document result. It does not explicitly name alternatives or exclusions, but the unique upload function among siblings makes the intended use apparent.

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