extract_pdf_textExtract the text content of a PDF — for RAG, summarization, or search. Accepts a file_id (from a prior tool) or a base64-encoded PDF, and returns the text inline. Not OCR: a scanned/image-only PDF returns little or no text.
| Name | Required | Description | Default |
|---|---|---|---|
| Yes | A file_id from a prior tool result, or a base64-encoded PDF. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully bears the responsibility for behavioral disclosure. It transparently states the output ('returns the text inline') and the limitation ('Not OCR'), giving agents a clear picture of expected behavior.
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 highly concise, using two sentences that front-load the core purpose and then add practical details (input forms, limitation). No redundant information; every sentence earns its place.
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 simple tool with no output schema, the description provides all necessary context: what it does, how to provide input, what to expect as output, and a critical limitation. An agent can confidently decide when and how to invoke it.
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?
The single parameter 'pdf' is described in the schema with clear meaning ('file_id from a prior tool result, or a base64-encoded PDF'), and the description reinforces this. This adds semantic value beyond the bare type, fully covering the parameter's purpose.
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 clearly states the action ('Extract the text content of a PDF') and specifies the resource, distinguishing it from siblings like rotate_pdf or merge_pdfs. It also mentions common use cases (RAG, summarization, search), making the purpose explicit.
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 provides explicit guidance on when to use the tool (for PDFs with text content) and when not to (scanned/image-only PDFs, since it's not OCR). It also clarifies input options (file_id or base64), leaving no ambiguity about usage scope.
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.
Most tools have clearly distinct purposes, such as extracting PDF text versus filling forms or rendering URLs to PDF versus screenshots. The only mild overlap is read_url and scrape_page, both fetching a URL, but their outputs are explicitly differentiated as clean Markdown versus raw HTML with metadata.
Names mostly follow a verb_noun pattern like extract_pdf_text, fill_pdf_form, and rotate_pdf. A few conversion tools use 'to' constructions (images_to_pdf, markdown_to_pdf, url_to_pdf) and some pluralize objects (merge_pdfs, select_pages), creating minor inconsistency but no real confusion.
With 15 tools, the set is at the upper edge of the ideal range and every tool serves a distinct, useful function within the PDF and URL processing domain. The count feels justified rather than excessive.
The PDF tooling covers creation from images and Markdown, text extraction, form filling and reading, merging, splitting, rotating, selecting pages, and watermarking. URL handling covers reading as Markdown, scraping raw HTML/metadata, generating PDFs, and taking screenshots, providing well-rounded coverage for the stated domain.