extract_pdf_textPull the text out of a PDF, page by page, so it can be read, summarised or analysed. Works on text-based PDFs, not on photos of pages.
| Name | Required | Description | Default |
|---|---|---|---|
| file | Yes | A single input file, given as either an HTTPS url or base64 contents. | |
| pages | No | Optional page selection such as "1-5" or "1, 3, 7". Defaults to the whole document. |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, idempotent, and open-world behavior. The description adds valuable context beyond those hints: output is returned page by page, and the tool is ineffective on scanned or image-based PDFs. It does not state the exact failure mode for scanned pages, but it gives a clear limitation.
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?
Two short, front-loaded sentences with no filler. Each clause contributes: the action, the output granularity, the use cases, and the critical scanned-PDF limitation.
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?
Given full schema coverage and annotations that establish safety and idempotence, the description covers the key non-obvious constraint (text-based only) and hints at return shape via 'page by page'. An explicit return-format contract would improve completeness, but nothing essential is missing for invoking the tool correctly.
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%, and the schema already explains the file object (url/base64/filename) and optional pages parameter. The description adds no parameter-specific detail, which is acceptable because the schema carries the semantic weight.
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 uses a specific verb ('Pull the text out') and resource ('a PDF'), and adds 'page by page' to convey granularity. It distinguishes itself from sibling PDF tools, none of which extract text content, and from get_pdf_info by focusing on text rather than metadata.
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 explicitly states when to use the tool (when PDF text needs to be read, summarised, or analysed) and when not to use it ('not on photos of pages'). It does not name a specific sibling alternative, but no sibling performs text extraction, so the guidance is sufficient.
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.