Docflow Upload And Extract

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

With no annotations, the description carries the full burden. It discloses that the call blocks until classification and extraction finish ('wait for... to complete') and enumerates supported formats. But it stays silent on side effects (files persist in the workspace), timeout/error behavior beyond the schema default, and how failures could be recovered via the retry siblings.

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, each earning its place: core behavior, input-mode rule, and format constraint. The main action is front-loaded, and there is zero filler or restatement of the title.

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?

An output schema covers return values and all six parameters are fully documented, so those burdens are lifted. Still, for a complex async mutation with zero annotation coverage, the description omits side-effect disclosure, timeout consequences, and the retry path — an agent cannot predict what happens when processing fails or times out.

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 coverage is 100%, baselining this at 3, but the description adds the either/or relationship between file_paths and directory ('Provide either...'), which is not expressible in the JSON schema. It also ties the supported-format list to what directory auto-scanning will pick up, giving an agent real selection guidance beyond the schema text.

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+resource pair: 'Upload files and wait for classification and extraction to complete.' It names the two invocation modes (explicit file_paths or auto-scanning directory) and clearly differentiates this ingestion tool from the sibling set, none of which handle uploads. The scope is unambiguous.

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?

It explains how to choose between the file_paths and directory inputs ('Provide either...'), and the supported-format list lets an agent pre-filter files. However, it never states when to prefer this tool over siblings like docflow_extract_fields, docflow_retry_files, or docflow_fetch_files, and gives no exclusions. When-not-to-use guidance must be inferred from the tool's name alone.

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