Extract words inside a specific bounding box on a PDF page or image in reading order. Use it to read a table column or page region without processing the full document.
The words inside a box on a page, in reading order: one column of a table read on its own.
| Name | Required | Description | Default |
|---|---|---|---|
| box | Yes | [x0, y0, x1, y1] in PDF points from the top left | |
| dpi | No | ||
| page | Yes | ||
| path | Yes | ||
| force_ocr | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full disclosure burden. It does contribute one behavioral trait ('in reading order'), but says nothing about whether words carry coordinates, what happens for an empty/invalid box, whether OCR is triggered, or what the response shape is. For a 5-parameter extraction tool with zero annotation coverage this is a substantial gap.
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 tight sentence with no filler, and the scope-defining element ('inside a box') is front-loaded. It is a sentence fragment that reads slightly cryptically ('words_in' as 'The words inside...'), which keeps it from a 5, but nothing is padded.
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 5 parameters, no annotations, no output schema, and 20% schema description coverage, the description is too thin to fully specify the tool. It establishes scope but omits return format, coordinate semantics, and the role of dpi/force_ocr, leaving real gaps an agent must guess at.
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 20% — just the box array is documented as '[x0, y0, x1, y1] in PDF points from the top left'; path, page, dpi, and force_ocr have no schema descriptions. The description mentions 'box' and 'page' only indirectly and never explains dpi or force_ocr, so it fails to compensate for the low coverage.
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 names a specific resource and scope: 'the words inside a box on a page, in reading order.' That is a clear, verifiable action (extract words from a region) and implicitly separates it from siblings that read whole pages or search. It does not name any sibling or explain how it differs from read_page/find, so it stays below a 5.
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 only implied through the phrase 'one column of a table read on its own,' which signals the region/column-extraction use case. There is no explicit when-to-use guidance versus read_page, read_pages, or find, and no stated prerequisites. Adequate but leaves the routing decision to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.