Extract Pages — Pull a chosen range of pages out of a PDF into a new PDF. To split a document into single pages, fixed chunks, or odd and even pages, use Split PDF instead. [category: pdf]
| Name | Required | Description | Default |
|---|---|---|---|
| file | Yes | Input PDF (max 25MB). The uploaded filename must end in .pdf. | |
| pages | Yes | Page range e.g. '2-5,8' | |
| outputName | No | Optional custom output basename. |
Changes observed during successful MCP inspections.
Input schema / properties / pages / titleAdded value: +"Pages to extract"Input schema / properties / pages / x-uiAdded value: +{
+ "no_recall": true,
+ "page_select": {}
+}Input schema / properties / outputName / x-uiAdded value: +{
+ "unset_label": "Named after your file"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=false, and the description reinforces this by saying the operation creates a new PDF rather than modifying the input. However, it does not add much behavioral detail beyond the annotations, such as handling of invalid page ranges or whether the original file is preserved.
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 two sentences with no wasted words: it states the action, the output, and the alternative in a front-loaded structure. The trailing [category: pdf] tag is unobtrusive metadata.
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 straightforward PDF utility, the description plus fully-covered schema provides everything an agent needs: what the tool does, what it returns (a new PDF), and how it differs from Split PDF. No critical gap remains.
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 the pages parameter already documented via the example '2-5,8' and the file schema stating the 25MB limit and .pdf requirement. The description adds no parameter-level meaning, so the baseline score of 3 applies.
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 and resource: 'Pull a chosen range of pages out of a PDF into a new PDF.' It clearly states what the tool does and explicitly contrasts it with Split PDF, making the tool's identity and scope easy to distinguish.
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 provides an explicit when-not-to-use condition and names the alternative: 'To split a document into single pages, fixed chunks, or odd and even pages, use Split PDF instead.' This is direct routing guidance for the agent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.