Converts raw PDF dumps, OCR text, tables, or unorganized notes into structured Markdown, JSON, or table formats for analysis and reuse.
Processes and structures raw dumps from PDFs, tables, unorganized notes, or OCR using Nemotron Parse 2.0
| Name | Required | Description | Default |
|---|---|---|---|
| raw_content | Yes | Raw unformatted content, PDF text dump, or OCR to parse. | |
| target_format | No | Desired output format. Default: 'markdown'. |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It names the engine but says nothing about whether the call is read-only vs. side-effecting, whether large inputs are chunked or truncated, latency/cost characteristics, or failure modes for unparseable content — significant gaps for a tool with zero annotation coverage.
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?
A single front-loaded sentence with no filler; the action, the accepted input types, and the engine are all delivered without repetition.
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?
With only two well-documented parameters and no output schema or annotations, the core call contract is covered by the schema. Still missing are output shape expectations (beyond the target_format enum) and any input-size or content-type limits an agent would need before sending a large dump.
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 both parameters documented including the enum values and the 'markdown' default, so the baseline is 3. The description adds no extra semantics about how raw_content should be prepared or how target_format affects fidelity.
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?
States a specific verb (processes/structures) and a specific resource (raw dumps from PDFs, tables, notes, OCR), plus names the underlying model. An agent can distinguish it from reasoning/vision siblings by the 'raw document content in, structured text out' framing, though no sibling is named explicitly.
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?
Usage is implied by the enumerated input types (PDF dumps, tables, notes, OCR), which tells an agent when this fits. However, there is no explicit 'use this instead of nim_analyze_vision when...' routing or any stated prerequisite, so the agent must infer the boundary with siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.