Upload a document

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

With annotations only indicating non-readOnly, non-idempotent, and non-destructive, the description adds meaningful behavior: consumption is asynchronous, a task ID is returned, and content_base64 incurs context cost proportional to file size. This goes beyond the schema and helps the agent anticipate consequences.

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, no filler, with the core purpose and critical operational details front-loaded. Every sentence earns its place: purpose, input-mode tradeoffs, and asynchronous behavior.

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?

For a 10-parameter tool with no output schema, the description covers the key decision (path vs content_base64), flags file-size limits, and explains the return value and follow-up path. It doesn't explain all optional metadata parameters, but those are largely inferable from names/schema. The main gap is not mentioning accepted file types or mutual-exclusivity constraints beyond 'provide either'.

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 only 40%, so the description carries extra responsibility. It adds important semantics for the two primary parameters (`path` vs `content_base64`), but it does not clarify relationships between other optional parameters like `filename` being required with `content_base64` — though the schema does cover that. The optional metadata fields are self-evident from names, but the description does not compensate for all low-coverage parameters.

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?

Description opens with a clear verb and resource: 'Hand a file to Paperless for consumption.' It distinguishes upload_document from sibling document actions by specifying ingestion of a file, and the path/content-mode detail reinforces the purpose. No ambiguity about what the tool does.

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 explicitly guides when to use `path` vs `content_base64`, labeling path as the cheap local option and content_base64 for remote deployments with a size caveat. It also directs the agent to get_task after the asynchronous upload. It doesn't name a sibling alternative, but the guidance within the tool is clear.

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